2008 ContextAwareRecommenderSystems

(Adomavicius & Tuzhilin, 2008) ⇒ Gediminas Adomavicius, and Alexander Tuzhilin. (2008). “Context-aware Recommender Systems.” In: Proceedings of the 2008 ACM Conference on Recommender Systems (RecSys-2008). ISBN:978-1-60558-093-7 doi:10.1145/1454008.1454068

Subject Headings: Context Aware Recommendation Algorithms, Context Record.

Notes

Cited By

Quotes

Abstract

The importance of contextual information has been recognized by researchers and practitioners in many disciplines, including e-commerce personalization, information retrieval, ubiquitous and mobile computing, data mining, marketing, and management. While a substantial amount of research has already been performed in the area of recommender systems, most existing approaches focus on recommending the most relevant items to users without taking into account any additional contextual information, such as time, location, or the company of other people (e.g., for watching movies or dining out). In this chapter we argue that relevant contextual information does matter in recommender systems and that it is important to take this information into account when providing recommendations. We discuss the general notion of context and how it can be modeled in recommender systems. Furthermore, we introduce three different algorithmic paradigms – contextual prefiltering, post-filtering, and modeling – for incorporating contextual information into the recommendation process, discuss the possibilities of combining several context - aware recommendation techniques into a single unifying approach, and provide a case study of one such combined approach. Finally, we present additional capabilities for context-aware recommenders and discuss important and promising directions for future research.

7.1 Introduction and Motivation

The majority of existing approaches to recommender systems focus on recommending the most relevant items to individual users and do not take into consideration any contextual information, such as time, place and the company of other people (e.g., for watching movies or dining out). In other words, traditionally recommender systems deal with applications having only two types of entities, users and items, and do not put them into a context when providing recommendations.

However, in many applications, such as recommending a vacation package, personalized content on aWeb site, or a movie, it may not be sufficient to consider only users and items – it is also important to incorporate the contextual information into the recommendation process in order to recommend items to users under certain circumstances. For example, using the temporal context, a travel recommender system would provide a vacation recommendation in the winter that can be very different from the one in the summer. Similarly, in the case of personalized content delivery on a Web site, it is important to determine what content needs to be delivered (recommended) to a customer and when. More specifically, on weekdays a user might prefer to read world news when she logs on in the morning and the stock market report in the evening, and on weekends to read movie reviews and do shopping. These observations are consistent with the findings in behavioral research on consumer decision making in marketing that have established that decision making, rather than being invariant, is contingent on the context of decision making. Therefore, accurate prediction of consumer preferences undoubtedly depends upon the degree to which the recommender system has incorporated the relevant contextual information into a recommendation method.

More recently, companies started incorporating some contextual information into their recommendation engines. For example, when selecting a song for the customer, Sourcetone interactive radio (www.sourcetone.com) takes into the consideration the current mood of the listener (the context) that she specified. In case of music recommenders, some of the contextual information, such as listener’s mood, may matter for providing better recommendations. However, it is still not clear if context matters for a broad range of other recommendation applications.

In this chapter we discuss the topic of context-aware recommender systems (CARS), address this and several other related questions, and demonstrate that, depending on the application domain and the available data, at least certain contextual information can be useful for providing better recommendations. We also propose three major approaches in which the contextual information can be incorporated into recommender systems, individually examine these three approaches, and also discuss how these three separate methods can be combined into one unified approach. Finally, the inclusion of the contextual information into the recommendation process presents opportunities for richer and more diverse interactions between the end-users and recommender systems. Therefore, in this chapter we also discuss novel flexible interaction capabilities in the form of the recommendation query language for context-aware recommender systems.

The rest of the chapter is organized as follows. Section 7.2 discusses the general notion of context as well as how it can be modeled in recommender systems. Section 7.3 presents three different algorithmic paradigms for incorporating contextual information into the recommendation process. Section 7.4 discusses the possibilities of combining several context-aware recommendation techniques and provides a case study of one such combined approach. Additional important capabilities for context-aware recommender systems are described in Section 7.5, and the conclusions and some opportunities for future work are presented in Section 7.6.

7.2 Context in Recommender Systems

Before discussing the role and opportunities of contextual information in recommender systems, in Section 7.2.1 we start by discussing the general notion of context. Then, in Section 7.2.2, we focus on recommender systems and explain how context is specified and modeled there.

7.2.1 What is Context?

Context is a multifaceted concept that has been studied across different research disciplines, including computer science (primarily in artificial intelligence and ubiquitous computing), cognitive science, linguistics, philosophy, psychology, and organizational sciences. In fact, an entire conference – CONTEXT (see, for example, http://context-07.ruc.dk) – is dedicated exclusively to studying this topic and incorporating it into various other branches of science, including medicine, law, and business. In reference to the latter, a well-known business researcher and practitioner C. K. Prahalad has stated that “the ability to reach out and touch customers anywhere at anytime means that companies must deliver not just competitive products but also unique, real-time customer experiences shaped by customer context” and that this would be the next main issue (“big thing”) for the CRM practitioners [57]. Since context has been studied in multiple disciplines, each discipline tends to take its own idiosyncratic view that is somewhat different from other disciplines and is more specific than the standard generic dictionary definition of context as “conditions or circumstances which affect some thing” [70]. Therefore, there exist many definitions of context across various disciplines and even within specific subfields of these disciplines. Bazire and Brézillon [17] present and examine 150 different definitions of context from different fields. This is not surprising, given the complexity and the multifaceted nature of the concept. As Bazire and Brézillon [17] observe:

“. . . it is difficult to find a relevant definition satisfying in any discipline. Is context a frame for a given object? Is it the set of elements that have any influence on the object? Is it possible to define context a priori or just state the effects a posteriori? Is it something static or dynamic? Some approaches emerge now in Artificial Intelligence [. . .]. In Psychology, we generally study a person doing a task in a given situation. Which context is relevant for our study? The context of the person? The context of the task? The context of the interaction? The context of the situation? When does a context begin and where does it stop? What are the real relationships between context and cognition?”

Since we focus on recommender systems in this paper and since the general concept of context is very broad, we try to focus on those fields that are directly related to recommender systems, such as data mining, e-commerce personalization, databases, information retrieval, ubiquitous and mobile context-aware systems, marketing, and management. We follow Palmisano et al. [54] in this section when describing these areas.

Data Mining. In the data mining community, context is sometimes defined as those events which characterize the life stages of a customer and that can determine a change in his/her preferences, status, and value for a company [18]. Examples of context include a new job, the birth of a child, marriage, divorce, and retirement. Knowledge of this contextual information helps (a) mining patterns pertaining to this particular context by focusing only on the relevant data; for example, the data pertaining to the daughter’s wedding, or (b) selecting only relevant results, i.e., those data mining results that are applicable to the particular context, such as the discovered patterns that are related to the retirement of a person.

E-commerce Personalization. Palmisano et al. [54] use the intent of a purchase made by a customer in an e-commerce application as contextual information. Different purchasing intents may lead to different types of behavior. For example, the same customer may buy from the same online account different products for different reasons: a book for improving her personal work skills, a book as a gift, or an electronic device for her hobby. To deal with different purchasing intentions, Palmisano et al. [54] build a separate profile of a customer for each purchasing context, and these separate profiles are used for building separate models predicting customer’s behavior in specific contexts and for specific segments of customers. Such contextual segmentation of customers is useful, because it results in better predictive models across different e-commerce applications [54].

Recommender systems are also related to e-commerce personalization, since personalized recommendations of various products and services are provided to the customers. The importance of including and using the contextual information in recommendation systems has been demonstrated in [3], where the authors presented a multidimensional approach that can provide recommendations based on contextual information in addition to the typical information on users and items used in many recommendation applications. It was also demonstrated by Adomavicius et al. [3] that the contextual information does matter in recommender systems: it helps to increase the quality of recommendations in certain settings.

Similarly, Oku et al. [53] incorporate additional contextual dimensions (such as time, companion, and weather) into the recommendation process and use machine learning techniques to provide recommendations in a restaurant recommender system. They empirically show that the context-aware approach significantly outperforms the corresponding non-contextual approach in terms of recommendation accuracy and user’s satisfaction with recommendations.

Since we focus on the use of context in recommender systems in this paper, we will describe these and similar approaches later in the chapter. Ubiquitous and mobile context-aware systems. In the literature pertaining to the context-aware systems, context was initially defined as the location of the user, the identity of people near the user, the objects around, and the changes in these elements [63]. Other factors have been added to this definition subsequently. For instance, Brown et al. [23] include the date, the season, and the temperature. Ryan et al. [61] add the physical and conceptual statuses of interest for a user. Dey et al. [33] include the user’s emotional status and broaden the definition to any information which can characterize and is relevant to the interaction between a user and an application. Some associate the context with the user [33, 35], while others emphasize how context relates to the application [60, 69]. More recently, a number of other techniques for context-aware systems have been discussed in research literature, including hybrid techniques for mobile applications [59, 71] and graphical models for visual recommendation [20].

This contextual information is crucial for providing a broad range of Location- Based Services (LBSes) to the mobile customers [64]. For example, a Broadway theater may want to recommend heavily discounted theater tickets to the Time Square visitors in New York thirty minutes before the show starts (since these tickets will be wasted anyway after the show begins) and send this information to the visitors’ smart phones or other communication devices. Note that time, location, and the type of the communication device (e.g., smart phone) constitute contextual information in this application. Brown et al. [22] introduce another interesting application that allows tourists interactively share their sightseeing experiences with remote users, demonstrating the value that context-aware techniques can provide in supporting social activities.

A survey of context-aware mobile computing research can be found in [30], which discusses different models of contextual information, context-sensing technologies, different possible architectures, and a number of context-aware application examples.

Databases. Contextual capabilities have been added to some of the database management systems by incorporating user preferences and returning different answers to database queries depending on the context in which the queries have been expressed and the particular user preferences corresponding to specific contexts. More specifically, in Stephanidis et al. [66] a set of contextual parameters is introduced and preferences are defined for each combination of regular relational attributes and these contextual parameters. Then Stephanidis et al. [66] present a context-aware extension of SQL to accommodate for such preferences and contextual information. Agrawal et al. [7] present another method for incorporating context and user preferences into query languages and develop methods of reconciling and ranking different preferences in order to expeditiously provide ranked answers to contextual queries. Mokbel and Levandoski [52] describe the context-aware and location-aware database server CoreDB and discuss several issues related to its implementation, including challenges related to context-aware query operators, continuous queries, multi-objective query processing, and query optimization.

Information Retrieval. Contextual information has been proven to be helpful in information retrieval and access [40], although most existing systems base their retrieval decisions solely on queries and document collections, whereas information about search context is often ignored [9]. The effectiveness of a proactive retrieval system depends on the ability to perform context-based retrieval, generating queries which return context-relevant results [46, 65]. In Web searching, context is considered as the set of topics potentially related to the search term. For instance, Lawrence [45] describes how contextual information can be used and proposes several specialized domain-specific context-based search engines. Integration of context into the Web services composition is suggested by Maamar et al. [51]. Most of the current context-aware information access and retrieval techniques focus on the short-term problems and immediate user interests and requests (such as “find all files created during a spring meeting on a sunny day outside an Italian restaurant in New York”), and are not designed to model long-term user tastes and preferences. Marketing and Management. Marketing researchers have maintained that the purchasing process is contingent upon the context in which the transaction takes place, since the same customer can adopt different decision strategies and prefer different products or brands depending on the context [19, 50]. According to Lilien et al. [47], “consumers vary in their decision-making rules because of the usage situation, the use of the good or service (for family, for gift, for self) and purchase situation (catalog sale, in-store shelf selection, and sales person aided purchase).” Therefore, accurate predictions of consumer preferences should depend on the degree to which we have incorporated the relevant contextual information. In the marketing literature, context has been also studied in the field of behavioral decision theory. In Lussier and Olshavsky [50], context is defined as a task complexity in the brand choice strategy.

The context is defined in Prahalad [57] as “the precise physical location of a customer at any given time, the exact minute he or she needs the service, and the kind of technological mobile device over which that experience will be received.” Further, Prahalad [57] focuses on the applications where the contextual information is used for delivering “unique, real-time customer experiences” based on this contextual information, as opposed to the delivery of competitive products. Prahalad [57] provides an example about the case when he left his laptop in a hotel in Boston, and was willing to pay significant premiums for the hotel shipping the laptop to him in New York in that particular context (he was in New York and needed the laptop really urgently in that particular situation).

To generalize his statements, Prahalad [57] really distinguishes among the following three dimensions of the contextual information: temporal (when to deliver customer experiences), spatial (where to deliver), and technological (how to deliver). Although Prahalad focuses on the real-time experiences (implying that it is really the present time, “now”), the temporal dimension can be generalized to the past and the future (e.g., I want to see a movie tomorrow in the evening). As this section clearly demonstrates, context is a multifaceted concept used across various disciplines, each discipline taking a certain angle and putting its “stamp” on this concept. To bring some “order” to this diversity of views, Dourish [34] introduces taxonomy of contexts, according to which contexts can be classified into the representational and the interactional views. In the representational view, context is defined with a predefined set of observable attributes, the structure (or schema, using database terminology) of which does not change significantly over time. In other words, the representational view assumes that the contextual attributes are identifiable and known a priori and, hence, can be captured and used within the context-aware applications. In contrast, the interactional view assumes that the user behavior is induced by an underlying context, but that the context itself is not necessarily observable. Furthermore, Dourish [34] assumes that different types of actions may give rise to and call for different types of relevant contexts, thus assuming a bidirectional relationship between activities and underlying contexts: contexts influence activities and also different activities giving rise to different contexts. In the next section, we take all these different definitions and approaches to context and adapt them to the idiosyncratic needs of recommender systems. As a result, we will also revise and enhance the prior definitions of context used in recommender systems, including those provided in [3, 53, 72].

7.2.2 Modeling Contextual Information in Recommender Systems

Recommender systems emerged as an independent research area in the mid-1990s, when researchers and practitioners started focusing on recommendation problems that explicitly rely on the notion of ratings as a way to capture user preferences for different items. For example, in case of a movie recommender system, John Doe may assign a rating of 7 (out of 10) for the movie “Gladiator,” i.e., set Rmovie(John Doe, Gladiator)=7. The recommendation process typically starts with the specification of the initial set of ratings that is either explicitly provided by the users or is implicitly inferred by the system. Once these initial ratings are specified, a recommender system tries to estimate the rating function R

R : User × Item → Rating

for the (user, item) pairs that have not been rated yet by the users. Here Rating is a totally ordered set (e.g., non-negative integers or real numbers within a certain range), and User and Item are the domains of users and items respectively. Once the function R is estimated for the whole User × Item space, a recommender system can recommend the highest-rated item (or k highest-rated items) for each user. We call such systems traditional or two-dimensional (2D) since they consider only the User and Item dimensions in the recommendation process.

In other words, in its most common formulation, the recommendation problem is reduced to the problem of estimating ratings for the items that have not been seen by a user. This estimation is usually based on the ratings given by this user to other items, ratings given to this item by other users, and possibly on some other information as well (e.g., user demographics, item characteristics). Note that, while a substantial amount of research has been performed in the area of recommender systems, the vast majority of the existing approaches focus on recommending items to users or users to items and do not take into the consideration any additional contextual information, such as time, place, the company of other people (e.g., for watching movies). Motivated by this, in this chapter we explore the area of context-aware recommender systems (CARS), which deal with modeling and predicting user tastes and preferences by incorporating available contextual information into the recommendation process as explicit additional categories of data. These long-term preferences and tastes are usually expressed as ratings and are modeled as the function of not only items and users, but also of the context. In other words, ratings are defined with the rating function as

R : User × Item × Context → Rating,

where User and Item are the domains of users and items respectively, Rating is the domain of ratings, and Context specifies the contextual information associated with the application. To illustrate these concepts, consider the following example. Example 7.1. Consider the application for recommending movies to users, where users and movies are described as relations having the following attributes: • Movie: the set of all the movies that can be recommended; it is defined as Movie(MovieID, Title, Length, ReleaseYear, Director, Genre). • User: the people to whom movies are recommended; it is defined as User(UserID, Name, Address, Age, Gender, Profession).

Further, the contextual information consists of the following three types that are also defined as relations having the following attributes: • Theater: the movie theaters showing the movies; it is defined as Theater( TheaterID, Name, Address, Capacity, City, State, Country). • Time: the time when the movie can be or has been seen; it is defined as Time(Date, DayOfWeek, TimeOfWeek, Month, Quarter, Year). Here, attribute DayOfWeek has values Mon, Tue, Wed, Thu, Fri, Sat, Sun, and attribute TimeOfWeek has values “Weekday” and “Weekend”. • Companion: represents a person or a group of persons with whom one can see a movie. It is defined as Companion(companionType), where attribute companionType has values “alone”, “friends”, “girlfriend/boyfriend”, “family”, “co-workers”, and “others”.

Then the rating assigned to a movie by a person also depends on where and how the movie has been seen, with whom, and at what time. For example, the type of movie to recommend to college student Jane Doe can differ significantly depending on whether she is planning to see it on a Saturday night with her boyfriend vs. on a weekday with her parents.

As we can see from this example and other cases, the contextual information Context can be of different types, each type defining a certain aspect of context, such as time, location (e.g., Theater), companion (e.g., for seeing a movie), purpose of a purchase, etc. Further, each contextual type can have a complicated structure reflecting complex nature of the contextual information. Although this complexity of contextual information can take many different forms, one popular defining characteristic is the hierarchical structure of contextual information that can be represented as trees, as is done in most of the context-aware recommender and profiling systems, including [3] and [54]. For instance, the three contexts from Example 1 can have the following hierarchies associated with them: Theater: TheaterID→City→ State → Country; Time: Date → DayOfWeek → TimeOfWeek, Date → Month → Quarter →Year.1

Furthermore, we follow the representational view of Dourish [34], as described at the end of Section 7.2.1, and assume that the context is defined with a predefined set of observable attributes, the structure of which does not change significantly over time. Although there are some papers in the literature that take the interactional approach to modeling contextual recommendations, such as [11] that models context through a short-term memory (STM) interactional approach borrowed from psychology, most of the work on context-aware recommender systems follows the representational view. As stated before, we also adopt this representational view in this chapter and assume that there is a predefined finite set of contextual types in a given application and that each of these types has a well-defined structure. More specifically, we follow Palmisano et al. [54], and also Adomavicius et al. [3] to some extent, in this paper and define the contextual information with a set of contextual dimensions K, each contextual dimension K in K being defined by a set of q attributes K = (K1, . . . ,Kq) having a hierarchical structure and capturing a particular type of context, such as Time or CommunicatingDevice. The values taken by attribute Kq define finer (more granular) levels, while K1 values define coarser (less granular) levels of contextual knowledge. For example, Figure 7.1(a) presents a four-level hierarchy for the contextual attribute K specifying the intent of a purchasing transaction in an e-retailer application. While the root (coarsest level) of the hierarchy for K defines purchases in all possible contexts, the next level is defined by attribute K1 = {Personal, Gift}, which labels each customer purchase either as a personal purchase or as a gift. At the next, finer level of the hierarchy, “Personal” value of attribute K1 is further split into a more detailed personal context: personal purchase made for the work-related or other purposes. Similarly, the Gift value for K1 can be split into a gift for a partner or a friend and a gift for parents or others. 1 For the sake of completeness, we would like to point out that not only the contextual dimensions, but also the traditional User and Item dimensions can have their attributes form hierarchical relationships. For example, the main two dimensions from Example 1 can have the following hierarchies associated with them: Movie: MovieID→Genre; User: UserID→Age, UserID→Gender, UserID → Profession.

Thus, the K2 level is K2 = {PersonalWork, PersonalOther, GiftPartner/Friend, Gift- Parent/Other}. Finally, attribute K2 can be split into further levels of hierarchy, as shown in Figure 7.1(a).2

Fig. 7.1: Contextual information hierarchical structure: (a) e-retailer dataset, (b) food dataset [54].

Contextual information was also defined in [3] as follows. In addition to the classical User and Item dimensions, additional contextual dimensions, such as Time, Location, etc., were also introduced using the OLAP-based3 multidimensional data (MD) model widely used in the data warehousing applications in databases [29, 41]. Formally, let D1,D2, . . . ,Dn be dimensions, two of these dimensions being User and Item, and the rest being contextual. Each dimension Di is a subset of a Cartesian product of some attributes (or fields) Ai j, (j = 1, . . . ,ki), i.e., Di ⊆ Ai1 ×Ai2 ×. . .×Aiki , where each attribute defines a domain (or a set) of values. Moreover, one or several attributes form a key, i.e., they uniquely define the rest of the attributes [58]. In some cases, a dimension can be defined by a single attribute, and ki =1 in such cases. For example, consider the three-dimensional recommendation space User×Item×Time, where the User dimension is defined as User ⊆ UName×Address×Income×Age and consists of a set of users having certain names, addresses, incomes, and being of a certain age. Similarly, the Item dimension is defined as Item ⊆ IName×Type×Price and consists of a set of items defined by their names, types and the price. Finally, the Time dimension can be defined as Time ⊆Year×Month×Day and consists of a list of days from the starting to the ending date (e.g. from January 1, 2003 to December 31, 2003). Given dimensions D1,D2, . . . ,Dn, we define the recommendation space for these dimensions as a Cartesian product S = D1 ×D2 ×. . .Dn. Moreover, let Rating be a rating domain representing the ordered set of all possible rating values. Then the rating function is defined over the space D1×. . .×Dn as R : D1×. . .×Dn →Rating.

2 For simplicity and illustration purposes, this figure uses only two-way splits. Obviously, threeway, four-way and, more generally, multi-way splits are also allowed.

3 OLAP stands for OnLine Analytical Processing, which represents a popular approach to manipulation and analysis of data stored in multi-dimensional cube structures and which is widely used for decision support.

For instance, continuing the User × Item × Time example considered above, we can define a rating function R on the recommendation space User × Item × Time specifying how much user u ∈ User liked item i ∈ Item at time t ∈ Time, R(u, i, t). Visually, ratings R(d1, . . . ,dn) on the recommendation space S = D1×D2×. . .× Dn can be stored in a multidimensional cube, such as the one shown in Figure 7.2. For example, the cube in Figure 7.2 stores ratings R(u, i, t) for the recommendation space User × Item × Time, where the three tables define the sets of users, items, and times associated with User, Item, and Time dimensions respectively. For example, rating R(101,7,1) = 6 in Figure 7.2 means that for the user with User ID 101 and the item with Item ID 7, rating 6 was specified during the weekday.

Fig. 7.2: Multidimensional model for the User × Item × Time recommendation space.

The rating function R introduced above is usually defined as a partial function, where the initial set of ratings is known. Then, as usual in recommender systems, the goal is to estimate the unknown ratings, i.e., make the rating function R total. The main difference between the multidimensional (MD) contextual model described above and the previously described contextual model lies in that contextual information in the MD model is defined using classical OLAP hierarchies, whereas the contextual information in the previous case is defined with more general hierarchical taxonomies, that can be represented as trees (both balanced and unbalanced), directed acyclic graphs (DAGs), or various other types of taxonomies. Further, the ratings in the MD model are stored in the multidimensional cubes, whereas the ratings in the other contextual model are stored in more general hierarchical structures. We would also like to point out that not all contextual information might be relevant or useful for recommendation purposes. Consider, for example, a book recommender system. Many types of contextual data could potentially be obtained by such a system from book buyers, including: (a) purpose of buying the book (possible options: for work, for leisure, . . .); (b) planned reading time (weekday, weekend, . . .); (c) planned reading place (at home, at school, on a plane, . . .); (d) the value of the stock market index at the time of the purchase. Clearly some types of contextual information can be more relevant in a given application than some other types. For example, in the previous example, the value of a stock market can be less relevant as contextual information than the purpose of buying a book. There are several approaches to determining the relevance of a given type of contextual information. In particular, the relevance determination can either be done manually, e.g., using domain knowledge of the recommender system’s designer or a market expert in a given application domain, or automatically, e.g., using numerous existing feature selection procedures from machine learning [42], data mining [48], and statistics [28], based on existing ratings data during the data preprocessing phase. The detailed discussion of the specific feature selection procedures is beyond the scope of this paper; in the remainder of this chapter we will assume that only the relevant contextual information is stored in the data.

7.2.3 Obtaining Contextual Information

The contextual information can be obtained in a number of ways, including:

• Explicitly, i.e., by directly approaching relevant people and other sources of contextual information and explicitly gathering this information either by asking direct questions or eliciting this information through other means. For example, a website may obtain contextual information by asking a person to fill out a web form or to answer some specific questions before providing access to certain web pages.

• Implicitly from the data or the environment, such as a change in location of the user detected by a mobile telephone company. Alternatively, temporal contextual information can be implicitly obtained from the timestamp of a transaction. Nothing needs to be done in these cases in terms of interacting with the user or other sources of contextual information – the source of the implicit contextual information is accessed directly and the data is extracted from it.

• Inferring the context using statistical or data mining methods. For example, the household identity of a person flipping the TV channels (husband, wife, son, daughter, etc.) may not be explicitly known to a cable TV company; but it can be inferred with reasonable accuracy by observing the TV programs watched

…

References

1. Christian Sengstock, Michael Gertz, Exploration and Comparison of Geographic Information Sources Using Distance Statistics, Proceedings of the 19th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, November 01-04, 2011, Chicago, Illinois
2. Christos Mettouris, Achilleas P. Achilleos, George Angelos Papadopoulos, A Context Modelling System and Learning Tool for Context-Aware Recommender Systems, Proceedings of the 8th European Conference on Scaling Up Learning for Sustained Impact, September 17-21, 2013
3. Claudio Biancalana, Andrea Flamini, Fabio Gasparetti, Alessandro Micarelli, Samuele Millevolte, Giuseppe Sansonetti, Enhancing Traditional Local Search Recommendations with Context-awareness, Proceedings of the 19th International Conference on User Modeling, Adaption, and Personalization, July 11-15, 2011, Girona, Spain
4. Bart P. Knijnenburg, Conducting User Experiments in Recommender Systems, Proceedings of the Sixth ACM Conference on Recommender Systems, September 09-13, 2012, Dublin, Ireland
5. Wim Verhavert, Jeroen Vanattenhoven, Dirk De Grooff, Improving Digital Reading Experiences with Mood-based Content Selection, CHI '13 Extended Abstracts on Human Factors in Computing Systems, April 27-May 02, 2013, Paris, France
6. Minsuk Kahng, Sangkeun Lee, Sang-goo Lee, Ranking in Context-aware Recommender Systems, Proceedings of the 20th International Conference Companion on World Wide Web, March 28-April 01, 2011, Hyderabad, India
7. Dietmar Jannach, Lukas Lerche, Michael Jugovac, Adaptation and Evaluation of Recommendations for Short-term Shopping Goals, Proceedings of the 9th ACM Conference on Recommender Systems, September 16-20, 2015, Vienna, Austria
8. Augusto Q. Macedo, Leandro B. Marinho, Rodrygo L.T. Santos, Context-Aware Event Recommendation in Event-based Social Networks, Proceedings of the 9th ACM Conference on Recommender Systems, September 16-20, 2015, Vienna, Austria
9. Rose Catherine, William Cohen, TransNets: Learning to Transform for Recommendation, Proceedings of the Eleventh ACM Conference on Recommender Systems, August 27-31, 2017, Como, Italy
10. Oleksiy Mazhelis, Indre Žliobaite, Mykola Pechenizkiy, Context-aware Personal Route Recognition, Proceedings of the 14th International Conference on Discovery Science, p.221-235, October 05-07, 2011, Espoo, Finland
11. Valentina Zanardi, Licia Capra, Dynamic Updating of Online Recommender Systems via Feed-forward Controllers, Proceedings of the 6th International Symposium on Software Engineering for Adaptive and Self-Managing Systems, May 23-24, 2011, Waikiki, Honolulu, HI, USA
12. Chih-Ming Chen, Ming-Feng Tsai, Yu-Ching Lin, Yi-Hsuan Yang, Query-based Music Recommendations via Preference Embedding, Proceedings of the 10th ACM Conference on Recommender Systems, September 15-19, 2016, Boston, Massachusetts, USA
13. Raafat Zarka, Amélie Cordier, Elöd Egyed-Zsigmond, Alain Mille, Contextual Trace-based Video Recommendations, Proceedings of the 21st International Conference Companion on World Wide Web, April 16-20, 2012, Lyon, France
14. Balázs Hidasi, Domonkos Tikk, Approximate Modeling of Continuous Context in Factorization Algorithms, Proceedings of the 4th Workshop on Context-Awareness in Retrieval and Recommendation, April 13-13, 2014, Amsterdam, The Netherlands
15. Andrei Rikitianskii, Morgan Harvey, Fabio Crestani, A Personalised Recommendation System for Context-Aware Suggestions, Proceedings of the 36th European Conference on IR Research on Advances in Information Retrieval, April 13-16, 2014, Amsterdam, The Netherlands
16. Licai Wang, Understanding and Using Contextual Information in Recommender Systems, Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval, July 24-28, 2011, Beijing, China
17. Luis Omar Colombo-Mendoza, Rafael Valencia-García, Alejandro Rodríguez-González, Giner Alor-Hernández, José Javier Samper-Zapater, RecomMetz, Expert Systems with Applications: An International Journal, v.42 n.3, p.1202-1222, February 2015
18. Mingjun Xin, Manli Lu, Weimin Li, An Adaptive Collaboration Evaluation Model and Its Algorithm Oriented to Multi-domain Location-based Services, Expert Systems with Applications: An International Journal, v.42 n.5, p.2798-2807, April 2015
19. Andrei Rikitianskii, Morgan Harvey, Fabio Crestani, A Personalised Recommendation System for Context-Aware Suggestions, Proceedings of the 36th European Conference on IR Research on Advances in Information Retrieval, April 13-16, 2014, Amsterdam, The Netherlands
20. Li Kuang, Gaofeng Cao, Liang Chen, Extracting Core Users Based on Features of Users and Their Relationships in Recommender Systems, International Journal of Web Services Research, v.14 n.2, p.1-23, April 2017
21. Martin Pichl, Eva Zangerle, Günther Specht, Understanding User-Curated Playlists on Spotify: A Machine Learning Approach, International Journal of Multimedia Data Engineering & Management, v.8 n.4, p.44-59, October 2017
22. Alexander Piazza, Pavlina Kröckel, Freimut Bodendorf, Emotions and Fashion Recommendations: Evaluating the Predictive Power of Affective Information for the Prediction of Fashion Product Preferences in Cold-start Scenarios, Proceedings of the International Conference on Web Intelligence, August 23-26, 2017, Leipzig, Germany
23. Lei Li, Li Zheng, Fan Yang, Tao Li, Modeling and Broadening Temporal User Interest in Personalized News Recommendation, Expert Systems with Applications: An International Journal, v.41 n.7, p.3168-3177, June, 2014
24. Linas Baltrunas, Bernd Ludwig, Francesco Ricci, Matrix Factorization Techniques for Context Aware Recommendation, Proceedings of the Fifth ACM Conference on Recommender Systems, October 23-27, 2011, Chicago, Illinois, USA
25. Alexandros Karatzoglou, Xavier Amatriain, Linas Baltrunas, Nuria Oliver, Multiverse Recommendation: N-dimensional Tensor Factorization for Context-aware Collaborative Filtering, Proceedings of the Fourth ACM Conference on Recommender Systems, September 26-30, 2010, Barcelona, Spain
26. Iván Cantador, Pablo Castells, Alejandro Bellogín, An Enhanced Semantic Layer for Hybrid Recommender Systems: Application to News Recommendation, International Journal on Semantic Web & Information Systems, v.7 n.1, p.44-78, January 2011
27. Pearl Pu, Li Chen, Rong Hu, Evaluating Recommender Systems from the User's Perspective: Survey of the State of the Art, User Modeling and User-Adapted Interaction, v.22 n.4-5, p.317-355, October 2012
28. Alexis Papadimitriou, Panagiotis Symeonidis, Yannis Manolopoulos, A Generalized Taxonomy of Explanations Styles for Traditional and Social Recommender Systems, Data Mining and Knowledge Discovery, v.24 n.3, p.555-583, May 2012
29. Nachiketa Sahoo, Param Vir Singh, Tridas Mukhopadhyay, A Hidden Markov Model for Collaborative Filtering, MIS Quarterly, v.36 n.4, p.1329-1356, December 2012
30. Roland Bader, Eugen Neufeld, Wolfgang Woerndl, Vivian Prinz, Context-aware POI Recommendations in An Automotive Scenario Using Multi-criteria Decision Making Methods, Proceedings of the 2011 Workshop on Context-awareness in Retrieval and Recommendation, p.23-30, February 13-13, 2011, Palo Alto, California
31. Balázs Hidasi, Domonkos Tikk, Context-aware Item-to-item Recommendation Within the Factorization Framework, Proceedings of the 3rd Workshop on Context-awareness in Retrieval and Recommendation, p.19-25, February 05-05, 2013, Rome, Italy
32. Ray Yun, Peter Scupelli, Azizan Aziz, Vivian Loftness, Sustainability in the Workplace: Nine Intervention Techniques for Behavior Change, Proceedings of the 8th International Conference on Persuasive Technology, p.253-265, April 03-05, 2013, Sydney, NSW, Australia
33. Yize Li, Jiazhong Nie, Yi Zhang, Bingqing Wang, Baoshi Yan, Fuliang Weng, Contextual Recommendation based on Text Mining, Proceedings of the 23rd International Conference on Computational Linguistics: Posters, p.692-700, August 23-27, 2010, Beijing, China
34. Christos Mettouris, George A. Papadopoulos, Ubiquitous Recommender Systems, Computing, v.96 n.3, p.223-257, March 2014
35. Liang Hong, Lei Zou, Cheng Zeng, Luming Zhang, Jian Wang, Jilei Tian, Context-Aware Recommendation Using Role-Based Trust Network, ACM Transactions on Knowledge Discovery from Data (TKDD), v.10 n.2, p.1-25, October 2015
36. Thuy-Ngoc Nguyen, An-Te Nguyen, Weighing the Role of Multi-criteria Communities for Recommender Systems, International Journal of Intelligent Engineering Informatics, v.3 n.4, p.330-348, November 2015
37. Qihua Liu, Xiaohong Gan, Combining User Contexts and User Opinions for Restaurant Recommendation in Mobile Environment, Journal of Electronic Commerce in Organizations, v.14 n.1, p.45-63, January 2016
38. Matteo Gaeta, Francesco Orciuoli, Luigi Rarità, Stefania Tomasiello, Fitted Q-iteration and Functional Networks for Ubiquitous Recommender Systems, Soft Computing - A Fusion of Foundations, Methodologies and Applications, v.21 n.23, p.7067-7075, December 2017
39. Tong Wang, Cynthia Rudin, Finale Doshi-Velez, Yimin Liu, Erica Klampfl, Perry MacNeille, A Bayesian Framework for Learning Rule Sets for Interpretable Classification, The Journal of Machine Learning Research, v.18 n.1, p.2357-2393, January 2017
40. Yong Zheng, Bamshad Mobasher, Robin Burke, User-Oriented Context Suggestion, Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization, July 13-17, 2016, Halifax, Nova Scotia, Canada
41. Wedad Hussein, Tarek F. Gharib, Rasha M. Ismail, Mostafa Gadal-Haqq M. Mostafa, A User-concept Matrix Clustering Algorithm for Efficient Next Page Prediction, International Journal of Knowledge and Web Intelligence, v.5 n.3, p.208-229, January 2016
42. Ramón Hermoso, Sergio Ilarri, Raquel Trillo, María Del Carmen Rodríguez-Hernández, Push-Based Recommendations in Mobile Computing Using a Multi-Layer Contextual Approach, Proceedings of the 13th International Conference on Advances in Mobile Computing and Multimedia, December 11-13, 2015, Brussels, Belgium
43. Alan Said, Identifying and Utilizing Contextual Data in Hybrid Recommender Systems, Proceedings of the Fourth ACM Conference on Recommender Systems, September 26-30, 2010, Barcelona, Spain
44. Negar Hariri, Bamshad Mobasher, Robin Burke, Query-driven Context Aware Recommendation, Proceedings of the 7th ACM Conference on Recommender Systems, October 12-16, 2013, Hong Kong, China
45. Linas Baltrunas, Francesco Ricci, Context-based Splitting of Item Ratings in Collaborative Filtering, Proceedings of the Third ACM Conference on Recommender Systems, October 23-25, 2009, New York, New York, USA
46. Umberto Panniello, Alexander Tuzhilin, Michele Gorgoglione, Comparing Context-aware Recommender Systems in Terms of Accuracy and Diversity, User Modeling and User-Adapted Interaction, v.24 n.1-2, p.35-65, February 2014
47. Umberto Panniello, Alexander Tuzhilin, Michele Gorgoglione, Cosimo Palmisano, Anto Pedone, Experimental Comparison of Pre- Vs. Post-filtering Approaches in Context-aware Recommender Systems, Proceedings of the Third ACM Conference on Recommender Systems, October 23-25, 2009, New York, New York, USA
48. Balázs Hidasi, Domonkos Tikk, Speeding Up ALS Learning via Approximate Methods for Context-aware Recommendations, Knowledge and Information Systems, v.47 n.1, p.131-155, April 2016
49. Yong Zheng, Bamshad Mobasher, Robin Burke, Context Recommendation Using Multi-label Classification, Proceedings of the 2014 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT), p.288-295, August 11-14, 2014
50. Bruno Pradel, Savaneary Sean, Julien Delporte, Sébastien Guérif, Céline Rouveirol, Nicolas Usunier, Françoise Fogelman-Soulié, Frédéric Dufau-Joel, A Case Study in a Recommender System based on Purchase Data, Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 21-24, 2011, San Diego, California, USA
51. Phung Do, Hung Nguyen, Vu Thanh Nguyen, Tran Nam Dung, A Context-Aware Recommendation Framework in E-Learning Environment, Proceedings of the Second International Conference on Future Data and Security Engineering, November 23-25, 2015, Ho Chi Minh City, Vietnam
52. Marcos AuréLio Domingues, AlíPio MáRio Jorge, Carlos Soares, Dimensions As Virtual Items: Improving the Predictive Ability of Top-N Recommender Systems, Information Processing and Management: An International Journal, v.49 n.3, p.698-720, May, 2013
53. Xin Li, Hsinchun Chen, Recommendation As Link Prediction in Bipartite Graphs, Decision Support Systems, v.54 n.2, p.880-890, January, 2013
54. Sahar Ebrahimi, Norha M. Villegas, Hausi A. Müller, Alex Thomo, SmarterDeals: A Context-aware Deal Recommendation System based on the Smartercontext Engine, Proceedings of the 2012 Conference of the Center for Advanced Studies on Collaborative Research, November 05-07, 2012, Toronto, Ontario, Canada
55. Yu Sun, Nicholas Jing Yuan, Yingzi Wang, Xing Xie, Kieran McDonald, Rui Zhang, Contextual Intent Tracking for Personal Assistants, Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 13-17, 2016, San Francisco, California, USA
56. Hui Gao, Duan-Bing Chen, Guan-Nan Wang, Dennis N. A Mensah, Yan Fu, A Continuous Rating Model for News Recommendation, Journal of Information Science, v.40 n.5, p.568-577, October 2014
57. Latifa Baba-Hamed, Reda Soltani, Improvement Quality of the Recommendation System Using the Intrinsic Context, Journal of Mobile Multimedia, v.9 n.3-4, p.189-213, March 2014
58. Eloisa Vargiu, Alessandro Giuliani, Giuliano Armano, Improving Contextual Advertising by Adopting Collaborative Filtering, ACM Transactions on the Web (TWEB), v.7 n.3, p.1-22, September 2013
59. Pierpaolo Basile, Marco De Gemmis, Leo Iaquinta, Pasquale Lops, Cataldo Musto, Fedelucio Narducci, Giovanni Semeraro, SpIteR: A Module for Recommending Dynamic Personalized Museum Tours, Proceedings of the 2009 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology, p.584-587, September 15-18, 2009
60. Licai Wang, Xiangwu Meng, Yujie Zhang, Yancui Shi, New Approaches to Mood-based Hybrid Collaborative Filtering, Proceedings of the Workshop on Context-Aware Movie Recommendation, p.28-33, September 30-30, 2010, Barcelona, Spain
61. Nafiseh Shabib, Gleb Sizov, John Krogstie, Product-aware Advertising, Proceedings of the 6th Euro American Conference on Telematics and Information Systems, May 23-25, 2012, Valencia, Spain
62. Boubenia Mohamed, Belkhir Abdelkader, Bouyakoub Fayçal M'hamed, A Multi-level Approach for Mobile Recommendation of Services, Proceedings of the International Conference on Internet of Things and Cloud Computing, p.1-6, March 22-23, 2016, Cambridge, United Kingdom
63. Balázs Hidasi, Domonkos Tikk, Fast ALS-based Tensor Factorization for Context-aware Recommendation from Implicit Feedback, Proceedings of the 2012th European Conference on Machine Learning and Knowledge Discovery in Databases, September 24-28, 2012, Bristol, UK
64. Balázs Hidasi, Domonkos Tikk, Fast ALS-Based Tensor Factorization for Context-aware Recommendation from Implicit Feedback, Proceedings of the 2012 European Conference on Machine Learning and Knowledge Discovery in Databases, September 24-28, 2012, Bristol, UK
65. Qiaoling Liu, Yandong Liu, Eugene Agichtein, Exploring Web Browsing Context for Collaborative Question Answering, Proceeding of the Third Symposium on Information Interaction in Context, August 18-21, 2010, New Brunswick, New Jersey, USA
66. Umberto Panniello, Michele Gorgoglione, Incorporating Context Into Recommender Systems: An Empirical Comparison of Context-based Approaches, Electronic Commerce Research, v.12 n.1, p.1-30, March 2012
67. Changjian Fang, Bo Mao, Jie Cao, Zhiang Wu, Exploiting Space-time Status for Service Recommendation, Proceedings of the 14th International Conference on Web Technologies and Applications, April 11-13, 2012, Kunming, China
68. Wenjun Yue, Meina Song, Jing Han, Haihong E, Location Context Aware Collective Filtering Algorithm, Proceedings of the 2012 International Conference on Pervasive Computing and the Networked World, p.788-800, November 28-30, 2012, Istanbul, Turkey
69. Ike Song, Chen Su, Peng Zhang, The Positive Role of Negative Ratings for Recommender, Proceedings of the 9th International Conference on Computer and Automation Engineering, February 18-21, 2017, Sydney, Australia
70. Feng Tan, Li Li, Zeyu Zhang, Yunlong Guo, A Multi-attribute Probabilistic Matrix Factorization Model for Personalized Recommendation, Pattern Analysis & Applications, v.19 n.3, p.857-866, August 2016
71. Umberto Panniello, Michele Gorgoglione, Cosimo Palmisano, Comparing Pre-filtering and Post-filtering Approach in a Collaborative Contextual Recommender System: An Application to E-Commerce, Proceedings of the 10th International Conference on E-Commerce and Web Technologies, September 01-04, 2009, Linz, Austria
72. Wenmin Wu, Jianli Zhao, Chunsheng Zhang, Fang Meng, Zeli Zhang, Yang Zhang, Qiuxia Sun, Improving Performance of Tensor-based Context-aware Recommenders Using Bias Tensor Factorization with Context Feature Auto-encoding, Knowledge-Based Systems, v.128 N.C, p.71-77, July 2017
73. Zhengxing Huang, Xudong Lu, Huilong Duan, Context-aware Recommendation Using Rough Set Model and Collaborative Filtering, Artificial Intelligence Review, v.35 n.1, p.85-99, January 2011
74. Jian Wang, Cheng Zeng, Chuan He, Liang Hong, Liang Zhou, Raymond K. Wong, Jilei Tian, Context-aware Role Mining for Mobile Service Recommendation, Proceedings of the 27th Annual ACM Symposium on Applied Computing, March 26-30, 2012, Trento, Italy
75. Marcos Aurélio Domingues, Camila Vaccari Sundermann, Marcelo Garcia Manzato, Ricardo Marcondes Marcacini, Solange Oliveira Rezende, Exploiting Text Mining Techniques for Contextual Recommendations, Proceedings of the 2014 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT), p.210-217, August 11-14, 2014
76. Benyou Zou, Cuiping Li, Liwen Tan, Hong Chen, GPUTENSOR, Information Sciences: An International Journal, v.299 N.C, p.159-177, April 2015
77. Yongli Ren, Gang Li, Wanlei Zhou, A Survey of Recommendation Techniques based on Offline Data Processing, Concurrency and Computation: Practice & Experience, v.27 n.15, p.3915-3942, October 2015
78. Sergio Ilarri, Ramón Hermoso, Raquel Trillo-Lado, María Del Carmen Rodríguez-Hernández, A Review of the Role of Sensors in Mobile Context-aware Recommendation Systems, International Journal of Distributed Sensor Networks, 2015, p.226-226, January 2015
79. Reza Khoshkangini, Maria Silvia Pini, Francesca Rossi, A Self-Adaptive Context-Aware Group Recommender System, Proceedings of the XV International Conference of the Italian Association for Artificial Intelligence on Advances in Artificial Intelligence, November 29-December 01, 2016
80. <a Href="/collection.cfm?id=KA1" Title="Artificial Intelligence" Target="_blank">Artificial Intelligence</a>
81. <a Href="/collection.cfm?id=KA3" Title="Digital Content" Target="_blank">Digital Content</a>
82. <a Href="/collection.cfm?id=KA6" Title="Interaction" Target="_blank">Interaction</a>
83. <a Href="/collection.cfm?id=KA7" Title="Networking" Target="_blank">Networking</a>
84. <a Href="/collection.cfm?id=KA8" Title="Software" Target="_blank">Software</a>
85.

}};

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2008 ContextAwareRecommenderSystems	Alexander Tuzhilin Gediminas Adomavicius			Context-aware Recommender Systems				10.1145/1454008.1454068		2008