Distinguishing IM Communication Patterns with Relationship and Conversation Topics

Kung Pai Lin, Hao Ping Lee, Yu Ling Chou, Faye Shih, Yung Ju Chang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Despite being characterized as constantly on and connected, IM users' responsiveness varies across different contacts. While research has shown that the relationship between conversation partners plays an important role in influencing their communication patterns, characterization of such patterns simply by using relationship information is limited [7, 8]. In this paper, we identify five distinct clusters of IM patterns using unsupervised learning derived from 46 users' conversation history. We show that the relationship category sufficed to characterize three clusters of communication patterns, but failed for the most active one. However, considering both relationship and topics would distinguish most communication patterns, including the most active one. This result suggests that future research on IM communication patterns should pay more attention to the topics in users' conversations.

Original languageEnglish
Title of host publicationCSCW 2021 - Conference Companion Publication of the 2021 Computer Supported Cooperative Work and Social Computing
PublisherAssociation for Computing Machinery
Pages121-125
Number of pages5
ISBN (Electronic)9781450384797
DOIs
StatePublished - 23 Oct 2021
Event24th ACM Conference on Computer-Supported Cooperative Work and Social Computing, CSCW 2021 - Virtual, Online, United States
Duration: 23 Oct 202127 Oct 2021

Publication series

NameProceedings of the ACM Conference on Computer Supported Cooperative Work, CSCW

Conference

Conference24th ACM Conference on Computer-Supported Cooperative Work and Social Computing, CSCW 2021
Country/TerritoryUnited States
CityVirtual, Online
Period23/10/2127/10/21

Fingerprint

Dive into the research topics of 'Distinguishing IM Communication Patterns with Relationship and Conversation Topics'. Together they form a unique fingerprint.

Cite this