Twitter content classification

From Brede Wiki
Jump to: navigation, search
Paper (help)
Twitter content classification
Authors: Stephen Dunn
Citation: First Monday 15 (12): missing pages. 2010 December
DOI: Define doi.
Web: Bing Google Yahoo!Google PDF
Article: BASE Google Scholar PubMed
Restricted: DTU Digital Library
Other: NIF
Format: BibTeX
Extract: Talairach coordinates from linked PDF: CSV-formated wiki-formated

Twitter content classification describes a classification of Twitter messages based on their content. The author analyzed his own Twitter stream consisting of 2841 messages from 2007 to 2009.

Dunn characterizes Twitter messages content categories first based on previous work by others.[1][2][3][4][5] Six categorizes are used:

  1. Conversation
  2. Pass along
  3. News
  4. Status
  5. Phatic
  6. Spam

The Pear Analytic study referenced would have News, Spam, Self-Promotion, Pointless Babble, Conversational and Pass-Along Value [4]

The paper makes a further level of classification, e.g., for "news" where the subcategories are:

  1. Headlines
  2. Sport
  3. Event
  4. Weather

The frequency of all news categories is rounded off to zero percent (13 out of 2841). In comparison the Pear Analytics study found 3.5% of tweets as news.[3]

[edit] Critique

  1. Analyzing ones own Twitter stream and reporting the frequency in the different categories have little generality, e.g., the author does not send spam.

[edit] References

  1. Akshay Java, Xiaodan Song, Tim Finin, Belle Tseng(2007). "Why we Twitter: understanding microblogging usage and communities". Pages 56-65 in Proceedings of the Ninth WEBKDD and First SNA–KDD Workshop on Web Mining and Social Network Analysis.
  2. B. Jansen, M. Zhang, K. Sobel, B. Tseng (2009). "Twitter power: Tweets as electronic word of mouth". Journal of the American Society for Information Science and Technology 60(11): 2169-2188. [1].
  3. 3.0 3.1 Pear Analytics, 2009, Twitter study. [2]
  4. C. Honeycutt, S. Herring (2009). "Beyond microblogging: Conversation and collaboration via Twitter". missing journal missing volume: 1-10. [3].
  5. M. Naaman, J. Boase, C.-H. Lai(2010). "Is it really about me? Message content in social awareness streams". Proceedings of the 2010 ACM Conference on Computer Supported Cooperative Work.
Personal tools