Context-aware recommender systems

By Gediminas Adomavicius, Alexander Tuzhilin. 2008

2,304 citations recorded by the source corpus.

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 contextaware 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.

Subfields: Computer Vision and Pattern Recognition, Information Systems, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Information Systems

In Signal Processing

Citations in the corpus

Explainable Recommendation: A Survey and New Perspectives (2018, neutral): “could be context-aware (Adomavicius and Tuzhilin, 2011).”
Or's of And's for Interpretable Classification, with Application to Context-Aware Recommender Systems (2015, background): “Such systems are called contextaware recommender systems (see surveys [1, 2, 5, 47] and references therein).”
Matrix factorization techniques for context aware recommendation (2011, background): “Categories and Subject Descriptors H.3.3 [Information Storage and Retrieval]: Information Search and Retrieval information .ltering General Terms Algorithms, Experimentation, Performance Keywords Recommender Systems, context-based reasoning, collaborative .ltering, matrix factorization 1.”
Collaborative Intent Prediction with Real-Time Contextual Data (2017, positive): “Besides time, context-aware recommendation models (Adomavicius and Tuzhilin 2011; Liu et al. 2013) try to incorporate more evidence of a specific situation such as the location, device, purchasing purpose, etc. to model the user preferences on unseen items.”
Current challenges and visions in music recommender systems research (2017, background): “ contentbased item descriptors. In contrast, we argue that satisfying the users’ musical entertainment needs requires taking into account intrinsic, extrinsic, and contextual aspects of the listeners [3], as well as more decent interaction information. For instance, personality and emotional state o”
General factorization framework for context-aware recommendations (2014, methodology): “…aware recommendation task accurately; (3) we compare the pointwise preference estimation, with the Bayesian Personalized Ranking (BPR; [9]); a pairwise learning strategy) and show that while BPR clearly outperforms pointwise preference estimation in the classical 2D MF setting, it seems to…”
Context-aware music recommendation based on latenttopic sequential patterns (2012, background): “Categories and Subject Descriptors H.3.3 [Information Search and Retrieval]: Information filtering Keywords recommender systems, collaborative filtering, context-aware recommendation”
Identifying and utilizing contextual data in hybrid recommender systems (2010, background): “The Workshop on Context-aware Recommender Systems (CARS) [1], which followed a tutorial on the same topic [3] one year prior, created a forum where current state of the art research could be shared with other members of the community.”
Collaborative Filtering beyond the User-Item Matrix (2014, background): “are directly related to the event of a user interacting (e.g., rating, purchasing) with an item [Adomavicius et al. 2011].”
Recommender system application developments: A survey (2015, methodology): “To incorporate the contextual information in recommender systems, Adomavicius and Tuzhilin [11] proposed a three-step process to make such information computable and valuable: Contextual Pre-Filtering, Contextual Post-Filtering, and Contextual Modeling.”
A generalized taxonomy of explanations styles for traditional and social recommender systems (2012, methodology): “For example, Context-aware algorithms (Adomavicius and Tuzhilin 2008) take into account for a recommendation any”
Semantic Multimedia Information Retrieval Based on Contextual Descriptions (2013, background): “Therefore, characteristics of context are defined to solve personalization problems in e-commerce and ubiquitous computing, to identify life stages of a person for data mining, or to improve online marketing and management [1].”
Mobile recommender systems in tourism (2014, background): “In addition to offering personalized recommendations through employing sophisticated user modeling methodologies, mobile tourism RSs may also take advantage of usage and application context in providing improved, context‐aware recommendations for attractions or tourist services [5],[34],[58].”
Daily-Aware Personalized Recommendation based on Feature-Level Time Series Analysis (2015, background): “Incorporating content information like product categories helps to build more accurate models [1, 9, 32], but such information is either absent in practical applications or difficult to generate and structure manually.”
The nice thing about context is that everyone has it (2015, methodology): “Across subfields like ubiquitous computing and recommender systems research, methods for defining, apprehending, and using ‘context’ are active areas of study (Adomavicius and Tuzhilin, 2011; Anand and Mobasher, 2007; Cooke et al., 2002; Dey, 2001; Lathia, 2014; Panniello et al., 2014).”
Interactive recommender systems: A survey of the state of the art and future research challenges and opportunities (2016, background): “In addition, there is a need for developing richer interaction capabilities for contextual recommender systems (Adomavicius and Tuzhilin, 2012).”