Twitter content classification
|Twitter content classification|
|Citation:||First Monday 15 (12): missing pages. 2010 December|
|Web:||Bing Google Yahoo! — Google PDF|
|Article:||BASE Google Scholar PubMed|
|Restricted:||DTU Digital Library|
|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.
- Pass along
The Pear Analytic study referenced would have News, Spam, Self-Promotion, Pointless Babble, Conversational and Pass-Along Value 
The paper makes a further level of classification, e.g., for "news" where the subcategories are:
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.
- Analyzing ones own Twitter stream and reporting the frequency in the different categories have little generality, e.g., the author does not send spam.
- ↑ 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.
- ↑ 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. .
- ↑ 3.0 3.1 Pear Analytics, 2009, Twitter study. 
- ↑ C. Honeycutt, S. Herring (2009). "Beyond microblogging: Conversation and collaboration via Twitter". missing journal missing volume: 1-10. .
- ↑ 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.