Sentiment Analytics for Monitoring and Analyzing Fan Page Posts

Harprith Kaur*, Randhawa and Deshinta*, Arrova Dewi and Lee, Wen Yi (2020) Sentiment Analytics for Monitoring and Analyzing Fan Page Posts. INTI JOURNAL, 2020 (21). ISSN e2600-7320

Text ij2020_21.pdf - Published Version Available under License Creative Commons Attribution. Download (311kB)

Abstract

One of the most significant ways to increase brand awareness or brand popularity in digital marketing is by connecting them directly with consumers via social media using fan pages. Fan pages allow consumers or users to interact with each other, discuss opinions, and create interactive dialogue engagement among the virtual community. This kind of active communication is preferred compared to websites that tend to do passive viewing of brand content. Public figures or personal brands use fan pages too to increase their popularity. Through fan pages, public figures establish an enduring and strong connection based on ongoing efforts to activate mutual interactions, shared values, rewards, experimental contents, positive actions, and others. An active and well-organized fan page will attract new visitors or new fans each day. This implies the extensive awareness of branding popularity and competitiveness which are driven by fan page and consumers. This paper studies the usage of sentiment analysis techniques to understand consumers’ preferences for different types of posts on a fan page. The sentiment analysis measures fan page’s effectiveness and analyzes metrics like calculate engagement rate, number of comments or shares, or likings in fan pages and others. The results of sentiment analysis are visualized and expected to advice on the next strategy or moves to increase the fans’ responsiveness. In this paper, the authors have analyzed data collection from Sina Weibo by scrapping data from webpages using URL, cookies, and user-agent based data. Webpage inspection and crawling were performed using mobile view and program implementation using Python, R languages and Tableau.

Item Type:	Article
Uncontrolled Keywords:	Semantic Analytics, Fan Pages, Data Mining, Dashboard
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:	Faculty of Information Technology
Depositing User:	Unnamed user with email masilah.mansor@newinti.edu.my
Date Deposited:	21 Oct 2020 05:18
Last Modified:	18 Mar 2024 05:42
URI:	http://eprints.intimal.edu.my/id/eprint/1436

Actions (login required)

View Item