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

被引:6
作者
Tanantong, Tanatorn [1 ]
Ramjan, Sarawut [2 ]
机构
[1] Thammasat Univ, Fac Sci & Technol, Dept Comp Sci, Bangkok, Thailand
[2] Thammasat Univ, AI Ctr, Coll Innovat, Bangkok, Thailand
关键词
Association Rule Mining; Demand and Supply Analysis; Social Media Analysis; MANAGEMENT;
D O I
10.4018/IJKSS.2021040101
中图分类号
C93 [管理学]; O22 [运筹学];
学科分类号
070105 ; 12 ; 1201 ; 1202 ; 120202 ;
摘要
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.
引用
收藏
页码:1 / 16
页数:16
相关论文
共 33 条
  • [1] Extraction of Unexpected Rules from Twitter Hashtags and its Application to Sport Events
    Adedoyin-Olowe, Mariam
    Gaber, Mohamed Medhat
    Dancausa, Carlos Martin
    Stahl, Frederic
    [J]. 2014 13TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA), 2014, : 207 - 212
  • [2] Agrawal R, 1994, P 20 INT C VER LARG
  • [3] Big Data Contextual Analytics Study on Arabic Tweets Summarization
    Al-Ibrahim, Fatimah
    Alzamil, Zakarya A.
    [J]. INTERNATIONAL JOURNAL OF KNOWLEDGE AND SYSTEMS SCIENCE, 2019, 10 (04) : 18 - 34
  • [4] Ali MM, 2014, IEEE STUDENT TECHNOL, P297, DOI 10.1109/TechSym.2014.6808064
  • [5] Non-Query-Based Pattern Mining and Sentiment Analysis for Massive Microblogging Online Texts
    Angel Diaz-Garcia, Jose
    Dolores Ruiz, M.
    Martin-Bautista, Maria J.
    [J]. IEEE ACCESS, 2020, 8 : 78166 - 78182
  • [6] [Anonymous], 2020, INTRO TWEET JSON
  • [7] [Anonymous], 2020, GETTING YOUR APPL TO
  • [8] Discovering generalized association rules from Twitter
    Cagliero, Luca
    Fiori, Alessandro
    [J]. INTELLIGENT DATA ANALYSIS, 2013, 17 (04) : 627 - 648
  • [9] Understanding the effect of social media marketing activities: The mediation of social identification, perceived value, and satisfaction
    Chen, Shih-Chih
    Lin, Chieh-Peng
    [J]. TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE, 2019, 140 : 22 - 32
  • [10] Chunmatcha N., 2016, THESIS SRIPATUM U TH