Personalized news recommendation based on implicit feedback

Ilievski, Ilija; Roy, Supriya

doi:10.1145/2516641.2516644

Cited by 31 publications

(12 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There have been many previous attempts to include these implicit feedbacks into news recommendations (Liu et al 2010). For instance, Ilievski and Roy (2013) introduce a framework to model user interest in individual news items using a taxonomy of hierarchical facets that capture various semantic aspects of a story that might appeal to the user. Lin et al (2014) focus on implicit social factors, such as opinions of experts and other influential persons, in news items recommendations.…”

Section: Implicit Signal Feedback In News Recommendationsmentioning

confidence: 99%

Affective recommender systems in online news industry: how emotions influence reading choices

Mizgajski¹,

Morzy

2018

User Model User-Adap Inter

View full text Add to dashboard Cite

Recommender systems have become ubiquitous over the last decade, providing users with personalized search results, video streams, news excerpts, and purchasing hints. Human emotions are widely regarded as important predictors of behavior and preference. They are a crucial factor in decision making, but until recently, relatively little has been known about the effectiveness of using human emotions in personalizing real-world recommender systems. In this paper we introduce the Emotion Aware Recommender System (EARS), a large scale system for recommending news items using user's self-assessed emotional reactions. Our original contribution includes the formulation of a multi-dimensional model of emotions for news item recommendations, introduction of affective item features that can be used to describe recommended items, construction of affective similarity measures, and validation of the EARS on a large corpus of real-world Web traffic. We collect over 13,000,000 page views from 2,700,000 unique users of two news sites and we gather over 160,000 emotional reactions to 85,000 news articles. We discover that incorporating pleasant emotions into collaborative filtering recommendations consistently outperforms all other algorithms. We also find that targeting recommendations by selected emotional reactions presents a promising direction for further research. As an additional contribution we share our experiences in designing and developing a real-world emotion-based recommendation engine, pointing to various challenges posed by the practical aspects of deploying emotion-based recommenders.

show abstract

Section: Implicit Signal Feedback In News Recommendationsmentioning

confidence: 99%

Affective recommender systems in online news industry: how emotions influence reading choices

Mizgajski¹,

Morzy

2018

User Model User-Adap Inter

View full text Add to dashboard Cite

show abstract

“…With the explosion of size of the training data, the ranking methods need use some efficient sampling techniques to reduce complexity. Finally, for BPR framework, there are a lot of special scenarios, such as recommending music [15], News [16], TV show [17] and POI [18,19], utilizing the additional information (e.g., POI recommender considers the geographical information) to improve prediction performance.…”

Section: Related Workmentioning

confidence: 99%

Local Weighted Matrix Factorization for Top-n Recommendation with Implicit Feedback

et al. 2016

View full text Add to dashboard Cite

Item recommendation helps people to discover their potentially interested items among large numbers of items. One most common application is to recommend topn items on implicit feedback datasets (e.g., listening history, watching history or visiting history). In this paper, we assume that the implicit feedback matrix has local property, where the original matrix is not globally low rank but some sub-matrices are low rank. In this paper, we propose Local Weighted Matrix Factorization (LWMF) for top-n recommendation by employing the kernel function to intensify local property and the weight function to model user preferences. The problem of sparsity can also be relieved by submatrix factorization in LWMF, since the density of submatrices is much higher than the original matrix. We propose a heuristic method to select sub-matrices which approximate the original matrix well. The greedy algorithm has approximation guarantee of factor 1 À 1 e to get a near-optimal solution. The experimental results on two real datasets show that the recommendation precision and recall of LWMF are both improved about 30% comparing with the best case of weighted matrix factorization (WMF).

show abstract

“…It is also not common for users to rate news articles and often the only information available is implicit in the logs of the users click patterns. This presents a particular challenge for collaborative filtering methods which rely on the opinions of similar users to generate recommendations [5], [9], [7].…”

Section: Related Workmentioning

confidence: 99%