An Association Rule Mining Approach to Discover Demand and Supply Patterns Based on Thai Social Media Data

Tanatorn Tanantong and Sarawut Ramjan
Additional contact information
Tanatorn Tanantong: Department of Computer Science, Faculty of Science and Technology, Thammasat University, Thailand
Sarawut Ramjan: Thammasat University AI Center, College of Innovation, Thammasat University, Thailand

International Journal of Knowledge and Systems Science (IJKSS), 2021, vol. 12, issue 2, 1-16

Abstract: In the digital age, social media technology has an important role as a communication platform for interpersonal interactions in the online virtual world. In addition, social media has impacted product exchange behavior in both vendors and buyers, with a shift from the traditional sales model to communication between parties via social media. Social media marketing, an online means of buying, selling, and exchanging goods and services, is increasingly popular due to convenience, speed, and greater choices. This trend has grown rapidly and is set to expand, leading to increased interest in research which analyzes and processes social media marketing data to gain a new integrated body of knowledge to better serve online business transactions. This research covers a new field, which may cause research and development limitations requiring background knowledge in several areas, such as digital technology, data analytics, and business analysis. This research aims to develop a framework to search for association rule mining of demand and supply data on social media platforms. Data is collected from Twitter and underwent cleansing and labeling for separating into five groups. Hashtag data from tweets is then extracted and transformed to input attributes of the framework. Next, association rule mining is performed using the Apriori algorithm in order to determine frequent items and extract candidate association rules. The last stage is rule selection, which uses Twitter-specific statistical attributes, that is, number of retweets and likes, to select highly effective association rules. The findings are that it is possible to mine association rules relating to demand and supply on Twitter. Based on an analysis of the association rule results, the content of those rules reflects trending activities and events at different times. Such information can be analyzed in further research to design improvements in social media marketing.

Date: 2021
References: Add references at CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://services.igi-global.com/resolvedoi/resolve. ... 018/IJKSS.2021040101 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:igg:jkss00:v:12:y:2021:i:2:p:1-16

Access Statistics for this article

International Journal of Knowledge and Systems Science (IJKSS) is currently edited by Van Nam Huynh

More articles in International Journal of Knowledge and Systems Science (IJKSS) from IGI Global
Bibliographic data for series maintained by Journal Editor ().