Nafiseh Shabib

Contextual recommendations for groups

Recommendation systems have received significant attention, with most of the proposed methods focusing on recommendations for single users. Recently, there are also approaches aiming at either group or context-aware recommendations. In this paper, we address the problem of contextual recommendations for groups. We exploit a hierarchical context model to extend a typical recommendation model to a general context-aware one that tackles the information needs of a group. We base the computation of contextual group recommendations on a subset of preferences of the users that present the most similar behavior to the group, that is, the users with the most similar preferences to the preferences of the group members, for a specific context. This subset of preferences includes the ones with context equal to or more general than the given context.

3rd International Workshop on News Recommendation and Analytics (INRA 2015)

The 3rd International Workshop on News Recommendation and Analytics (INRA 2015) is held in conjunction with RecSys 2015 Conference in Vienna, Austria. This paper presents a brief summary of the INRA 2015. This workshop aims to create an interdisciplinary community that addresses design issues in news recommender systems and news analytics, and promote fruitful collaboration opportunities between researchers, media companies and practitioners. We have a keynote speaker and an invited demo presentation in addition to 4 papers accepted in this workshop.

Product-aware advertising

We propose an approach to context-aware advertising in which context is defined by the products currently used by a consumer. Unlike more traditional approaches, consumers are neither identified nor tracked; instead, products are tagged. An interesting use-case scenario for this model is a product-aware outdoor advertising system that dynamically selects a product to advertise based on the products identified for one person or a group of people nearby. For example, RFID tags integrated into clothing of someone passing by a digital billboard could allow for determining preferences regarding style, fashion and brands. This information would be used by a digital billboard with an RFID reader to recommend and advertise complementary and other products. There would be no inherent connection between product information and the identity of the consumer; and therefore the privacy of the consumer would not be violated. Tagging and tracking of consumer products provides opportunities for more personalized and engaging marketing experiences without introducing a privacy risk.