An Effective News Recommendation Method for Microblog User

Abstract

Recommending news stories to users, based on their preferences, has long been a favourite domain for recommender systems research. Traditional systems strive to satisfy their user by tracing users' reading history and choosing the proper candidate news articles to recommend. However, most of news websites hardly require any user to register before reading news. Besides, the latent relations between news and microblog, the popularity of particular news, and the news organization are not addressed or solved efficiently in previous approaches. In order to solve these issues, we propose an effective personalized news recommendation method based on microblog user profile building and sub class popularity prediction, in which we propose a news organization method using hybrid classification and clustering, implement a sub class popularity prediction method, and construct user profile according to our actual situation. We had designed several experiments compared to the state-of-the-art approaches on a real world dataset, and the experimental results demonstrate that our system significantly improves the accuracy and diversity in mass text data.

News recommender system: a review of recent progress, challenges, and opportunities

“…Some well-known metrics are: Intra-List Similarity (ILS) (similarity between any two lists of recommended items); temporal or Lathia’s diversity (in the sequence of recommendation lists over time); normalized diversity; and other measures as discussed by Kunaver and Porl (Kunaver and Porl 2017 ). The traditional pairwise diversity ILS remains a popular metric to evaluate diversity in NRS (Li and Li 2013 ; Gu et al 2014 ; Maksai et al 2015 ; Raza and Ding 2020 ). The ILS can be computed among the items, topics, categories, tags or even sentiments (tone) (Helberger 2019 ) in an NRS.…”

News Recommendation Systems - Accomplishments, Challenges & Future Directions

“…News recommendation systems can be broadly classified under two types based on the approach adapted that take advantages of social networking sites support news recommendations to news readers [45]. Different personalized news recommendation systems adopted social networking sites for community description [1], topic evolving on a forum [69], using mining techniques for constructing user profile [34] and more sophisticated techniques like personalization based on location, Twitter and Facebook profiling [48] etc., which help in news personalization. Facebook online news recommendation system [1] is proposed to provide daily newsletters for communities on Facebook based on community description.…”

“…A personalized news recommendation system using latent relationship of news article and microblog is presented in [34]. The news organization method is using a hybrid classification and clustering to predict by constructing user profile.…”

A Nondisturbing Service to Automatically Customize Notification Sending Using Implicit-Feedback

“…Extracting information from the users' tweets is another strategy to build the user's models for recommendations [30]. Gu et al [31] propose an approach that uses content in microblog or tweets of users and users' social network preferences (popularity) for news recommendations. Also, content in microblogs is taken into account for recommendations by Zheng and Wang [32], but from a sentimental point of view.…”