Predicting user interests from contextual information

TLDR

Search and recommendation systems must incorporate contextual information to effectively model users' interests. The study systematically evaluates the effectiveness of five contextual information sources—social, historic, task, collection, and user interaction—for modeling user interests. The authors focused on website recommendations, using these five sources and assessing their predictive utility and overlap for future interest prediction. The study shows that post‑query navigation and general browsing dominate information gathering, that contextual source performance varies with prediction window length, and that overlapping contexts outperform any single source, offering guidance for website recommendation design.

Abstract

Search and recommendation systems must include contextual information to effectively model users' interests. In this paper, we present a systematic study of the effectiveness of five variant sources of contextual information for user interest modeling. Post-query navigation and general browsing behaviors far outweigh direct search engine interaction as an information-gathering activity. Therefore we conducted this study with a focus on Website recommendations rather than search results. The five contextual information sources used are: social, historic, task, collection, and user interaction. We evaluate the utility of these sources, and overlaps between them, based on how effectively they predict users' future interests. Our findings demonstrate that the sources perform differently depending on the duration of the time window used for future prediction, and that context overlap outperforms any isolated source. Designers of Website suggestion systems can use our findings to provide improved support for post-query navigation and general browsing behaviors.