Follower classification based on user behavior for issue clusters

  • Kwang Yong Jeong
  • , Jae Wook Seol
  • , Kyung Soon Lee*
  • *Corresponding author for this work

    Research output: Contribution to conferenceConference paperpeer-review

    Abstract

    Recently, Social Network Service has made a meteoric rise as means of communication to sharing important information. peoples discuss about social issues, especially in Twitter. Besides, unlike any other social network service, Twitter users can follow without the agreement of the other party, for this reason, the users has followers with various intentions exist. To measure followers's agree about a followee's opinion, our method builds issue clusters by defining trust period about extracting an issue. In this paper, we propose two methods for follower classification that are based on extraction of Influential supporters and issues cluster that is reflected on a target user's opinion. To evaluate the effectiveness of the proposed method, we examine behaviors of followers of politicians from Twitter data. As a result of the experiment, the proposed approach effectively classifies the follower based on issues reflected opinions of the target user and Influential supporters.

    Original languageEnglish
    Title of host publicationProceedings of the First International Conference on Advanced Data and Information Engineering, DaEng 2013
    PublisherSpringer Verlag
    Pages143-150
    Number of pages8
    ISBN (Print)9789814585170
    DOIs
    StatePublished - 2014
    Event1st International Conference on Advanced Data and Information Engineering, DaEng 2013 - Kuala Lumpur, Malaysia
    Duration: 2013.12.162013.12.18

    Publication series

    NameLecture Notes in Electrical Engineering
    Volume285 LNEE
    ISSN (Print)1876-1100
    ISSN (Electronic)1876-1119

    Conference

    Conference1st International Conference on Advanced Data and Information Engineering, DaEng 2013
    Country/TerritoryMalaysia
    CityKuala Lumpur
    Period13.12.1613.12.18

    Keywords

    • Follower classification
    • Issue cluster
    • Social opinion
    • User behavior

    Quacquarelli Symonds(QS) Subject Topics

    • Engineering - Mechanical

    Fingerprint

    Dive into the research topics of 'Follower classification based on user behavior for issue clusters'. Together they form a unique fingerprint.

    Cite this