Modeling Users' Localized Preferences for More Effective News Recommendation

Payam Pourashraf, Bamshad Mobasher

Abstract: During the past two decades, Local newspapers have been experiencing major declines in readership due to the proliferation of national and global online news sources. Local media companies, whose predominant business model is subscription-based, need to increase user engagement to provide added value for local subscribers. Personalization and recommender systems are one way for these news companies to accomplish this goal. However, using standard modeling approaches that focus on users’ global preferences is not appropriate in this context because the local preferences of users exhibit some specific characteristics which do not necessarily match their long-term or broader preferences in the news. Our research explores a localized session-based recommendation approach, using recommendations based on local news articles and articles pertaining to the different local news categories. Experiments performed on a news dataset from a local newspaper show that these local models, particularly related to certain categories of items, do indeed provide more accuracy and effectiveness for personalization which, in turn, may lead to more user engagement with local news content.