Preface to the special issue on context-aware recommender systems

Abstract

Context-aware recommender systemsRecommender systems represent a popular area of personalization technologies that has enjoyed a tremendous amount of research and development activity in both academia and industry in the last 10-15 years. Recommender systems research typically explores and develops techniques and applications for recommending various products or services to individual users based on the knowledge of users' tastes and preferences as well as users' past activities (such as previous purchases), which are applicable in a variety of domains and settings (Jannach et al. 2010).While a substantial amount of research has already been performed in the area of recommender systems, many existing approaches have focused on recommending the most relevant items to users and do not take into account any additional contextual information, such as time, location, weather, the user's current goals, the user's mood, presence of other people, or the type of the device through which the recommendation is consumed. 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, the importance of contextual information has been recognized by researchers and practitioners in many

The Role of Context for Recommendations in Digital Libraries

“…It seems that trying to reach a consensual definition for context which is applicable for all domains is an ineffectual effort because context is a concept from the real world and it is impossible to delimit its territories by giving a certain definition [16] .Moreover, people comprehend phenomena by an interpretive understanding which is dependent on the contexts they are. Hermeneutic theory widely discusses that contexts change the epistemological criteria because context evokes different impressions in each reader therefore some researches have mentioned that context is a dynamic theorem [53].…”

“…Recently, contextual information modelling has been applied to improve classical recommendations in order to determine the status of status of people, places, objects and devices in the environment and improve the accuracy of recommendations. However, identifying and applying valid contextual information for different domains and users are challenges that should be addressed [45] these challenges have become a paradigm shift in recommending approaches in the recent years [16].…”

“…Many disciplines are involved in creating recommendation systems including Computer Science, Social Science, Cognitive Science, Business Science, Linguistic Science, Information Science and other related fields which make such systems an interdisciplinary research area [16]. At present, contextual information has been employed as a main source for the accuracy of predictions in RSs [42].…”

“…From the appearance of RSs as an independent research area in the mid-1990s [11], [12], many studies have been done on RSs in different domains [13]. Several studies have been done on them due to their effectiveness and performance in difference applications [14] however the issue of creating more accurate and relevant recommendations for users is still open and significant [15], [16]. In recent years, studies on RSs have been actuated to use contextual information such as location, time, and task in order to make more relevant and personalised recommendations [11], [12].…”

Modeling User Behaviors to Enable Context-Aware Proactive Decision Support

“…This approach improved recommendations by combining machine learning techniques with rules in a structured workflow. This combination of statistical inference, bounded by domain logic to guide user decision-making is a foundational characteristic of RS, particularly contextually aware RS [39]. Despite the richness of research on RS, research on RS for data exploration and analytical applications is sparse.…”