A content-location-aware public welfare activity information push system based on microblog. Issue 1 (January 2020)

• Record Type: Journal Article
• Authors: Chen, Ling; Lyu, Dandan; Xu, Zhenxing; Long, Hanyu; Chen, Gencai
• Is Part Of: Information processing & management. Volume 57:Issue 1(2020:Jan.)
• Publication Date: 2020-01
• Subjects: Location-aware -- Public welfare activity -- Information push system -- Microblog; Information storage and retrieval systems -- Periodicals; Information science -- Periodicals; Systèmes d'information -- Périodiques; Sciences de l'information -- Périodiques; Information science; Information storage and retrieval systems; Periodicals; 658.4038
• DOI: 10.1016/j.ipm.2019.102137
• Languages: English
• ISSNs: 0306-4573

Abstract

Highlights: Propose a content-location-aware public welfare activity information push system based on microblog. Propose a topic model and keyword search based method to discover users who are explicitly interested in public welfare activity information. Propose a distance metric learning based method to obtain a certain number of local potential users. Abstract: Microblog has become a widely used social media tool, which can help users publish or obtain Public Welfare Activity (PWA) information. Due to the characteristics of large-scale and arbitrary in microblog use, a large amount of messy information is produced, which makes it difficult to discover interesting PWA information. Thus, developing a push system, which can seek a certain number of local potential users for a PWA to be Pushed (PWAP), would be a great help. However, it is challenging to discover users explicitly interested in PWAs and obtain a certain number of local potential users. In this paper, a Content-Location-Aware PWA information Push system based on microblog (CLAP) is proposed, which can seek a certain number of local potential users for a PWAP from massive microblog users, and push the corresponding information to them. Specifically, a topic model and keyword search based method is firstly utilized to discover users who are explicitly interested in the PWAP (i.e., seed users). Secondly, a distance metric learning based method is utilized to obtain a certain number of local potential users by measuring the similarities between seed users and local users. Experimental results demonstrate that the proposed system has a potential to generate superior results.