Topicality, time, and sentiment in online news comments

Nicholas Diakopoulos*, Mor Naaman

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

21 Scopus citations


In this paper we examine the relationships between news comment topicality, temporality, sentiment, and quality in a dataset of 54, 540 news comments. Initial observations indicate that comment sentiments, both positive and negative, can be useful indicators of discourse quality, and that aggregate temporal patterns in positive sentiment exist on comment threads.

Original languageEnglish (US)
Title of host publicationCHI EA 2011 - 29th Annual CHI Conference on Human Factors in Computing Systems, Conference Proceedings and Extended Abstracts
PublisherAssociation for Computing Machinery
Number of pages6
ISBN (Print)9781450302289
StatePublished - 2011

Publication series

NameConference on Human Factors in Computing Systems - Proceedings


  • Commenting systems
  • News discourse
  • Online journalism

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Graphics and Computer-Aided Design


Dive into the research topics of 'Topicality, time, and sentiment in online news comments'. Together they form a unique fingerprint.

Cite this