Expertise-aware news feed updates recommendation: a random forest approach
- PDF / 1,087,986 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 111 Downloads / 253 Views
(0123456789().,-volV)(0123456789().,-volV)
Expertise-aware news feed updates recommendation: a random forest approach Sami Belkacem1
•
Kamel Boukhalfa1 • Omar Boussaid2
Received: 26 February 2019 / Revised: 10 July 2019 / Accepted: 22 October 2019 Springer Science+Business Media, LLC, part of Springer Nature 2019
Abstract With social media being widely used around the world, and because of the large amount of data, users are overcome by updates displayed chronologically in their news feed. Furthermore, most updates are considered irrelevant. To help beneficiary users quickly catch up with the relevant content, ranking news feed updates in descending relevance order has been achieved based on the prediction of a relevance score between a beneficiary and a new update in the news feed. Four types of features are generally used to predict the relevance: (1) the relevance of the update content to the beneficiary’s interests; (2) the social tie strength between the beneficiary and the update’s author; (3) the author’s authority; and (4) the update quality. In this work, from the biography and the textual content posted, we propose an approach that infers and uses another type of feature which is the expertise of the update’s author for the corresponding topic. Following extensive experiments on a real dataset crawled from Twitter, the results show that infer the author’s expertise is critical for identifying relevant updates in news feeds. Keywords Social media News feed updates Relevance Ranking Expertise Twitter
1 Introduction Social media such as Facebook, Twitter, and LinkedIn are used by hundreds of millions of users worldwide and contribute to the concept of Big data [1]. Social data are known for their large volumes that can reach petabytes (1015 bytes), their variety (text, images, videos, music, etc.), and their velocity (arriving near real-time) [2]. Due to the large amount of data posted and shared [3] on social media [3], users are overcome by a flow of updates displayed chronologically in their news feed [4]. For example, a survey of 587 Twitter users showed that 66.3% of them feel they cannot keep up with the large volume of updates
& Sami Belkacem [email protected] Kamel Boukhalfa [email protected] Omar Boussaid [email protected] 1
LSI laboratory, USTHB, Algiers, Algeria
2
ERIC laboratory, University Lyon 2, Lyon, France
in their news feed [5]. Moreover, most of these updates are considered irrelevant [6]. For example, a survey of 56 Twitter users indicated that users lose the most relevant tweets in a news feed of thousands of less useful tweets [7]. Therefore, large data volume and irrelevance make it difficult for users to catch up with the relevant updates in their news feed [8]. In several research approaches, ranking news feed updates in descending relevance order has been achieved based on the prediction of a relevance score between a beneficiary user and a new update in the news feed [9]. These approaches generally use four types of features that may influence r
Data Loading...
