M
Magdalini Eirinaki
Researcher at San Jose State University
Publications - 75
Citations - 3043
Magdalini Eirinaki is an academic researcher from San Jose State University. The author has contributed to research in topics: Recommender system & Personalization. The author has an hindex of 20, co-authored 72 publications receiving 2772 citations. Previous affiliations of Magdalini Eirinaki include Athens University of Economics and Business.
Papers
More filters
Proceedings ArticleDOI
With a Little Help from My Friends (and Their Friends): Influence Neighborhoods for Social Recommendations
Avni Gulati,Magdalini Eirinaki +1 more
TL;DR: This work creates neighborhoods of influence leveraging only the social graph structure that are introduced in the recommendation process both as a pre-processing step and as a social regularization factor of the matrix factorization algorithm.
Proceedings ArticleDOI
PRO-fit: exercise with friends
Saumil Dharia,Vijesh Jain,Jvalant Patel,Jainikkumar Vora,Rizen Yamauchi,Magdalini Eirinaki,Iraklis Varlamis +6 more
TL;DR: Pro-Fit is presented, a personalized fitness assistant application that employs machine learning and recommendation algorithms in order to smartly track and identify user's activity, synchronizes with the user's calendar, and recommends personalized workout sessions based on the user’s preferences, fitness goals, and availability.
Proceedings ArticleDOI
Influence Propagation for Social Graph-based Recommendations
Avni Gulati,Magdalini Eirinaki +1 more
TL;DR: This work model the decay in influence propagation in directed graphs, utilizing the structural properties of the social graph to measure the propagated influence beyond one-hop and employs this influence propagation model to form social recommendations, and presents experimental results using real-life datasets.
Proceedings ArticleDOI
AskUs: An Opinion Search Engine
TL;DR: This demonstration presents AskUs, a search engine that highlights opinions about the search results, which analyses the overall sentiment of a document/review, but also identifies the semantic orientation of specific components of the review that lead to a particular sentiment.