Skip to main content
placeholder image

Temporal sentiment detection for user generated video product reviews

Conference Paper


Download full-text (Open Access)

Abstract


  • User generated video product reviews in social media gaining popularity every day due to its creditability and the broad evaluation context provided by it. Extracting sentiment automatically from such videos will help the consumers making decisions and producers improving their products. This paper investigates the feasibility of sentiment detection temporally from those videos by analyzing the transcription generated by a speech recognition system which was not investigated before. Another two main contribution for this paper is introducing a solution to the problem of fixed threshold estimation for the Naïve Bayesian classifier output probabilities and irrelative text filtering for improving the sentiment classification. Various experiments indicated the proposed system can achieve an F-score of 0.66 which is promising knowing that the sentiment classifier offers an F-score of 0.78 provided that the input text is error free.

Publication Date


  • 2013

Citation


  • M. S. Barakat, C. H. Ritz & D. A. Stirling, "Temporal sentiment detection for user generated video product reviews," in 13th International Symposium on Communications and Information Technologies: Communication and Information Technology for New Life Style Beyond the Cloud, ISCIT 2013, 2013, pp. 580-584.

Scopus Eid


  • 2-s2.0-84891093375

Ro Full-text Url


  • http://ro.uow.edu.au/cgi/viewcontent.cgi?article=2958&context=eispapers

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/1949

Start Page


  • 580

End Page


  • 584

Place Of Publication


  • http://iscit2013.org/content/

Abstract


  • User generated video product reviews in social media gaining popularity every day due to its creditability and the broad evaluation context provided by it. Extracting sentiment automatically from such videos will help the consumers making decisions and producers improving their products. This paper investigates the feasibility of sentiment detection temporally from those videos by analyzing the transcription generated by a speech recognition system which was not investigated before. Another two main contribution for this paper is introducing a solution to the problem of fixed threshold estimation for the Naïve Bayesian classifier output probabilities and irrelative text filtering for improving the sentiment classification. Various experiments indicated the proposed system can achieve an F-score of 0.66 which is promising knowing that the sentiment classifier offers an F-score of 0.78 provided that the input text is error free.

Publication Date


  • 2013

Citation


  • M. S. Barakat, C. H. Ritz & D. A. Stirling, "Temporal sentiment detection for user generated video product reviews," in 13th International Symposium on Communications and Information Technologies: Communication and Information Technology for New Life Style Beyond the Cloud, ISCIT 2013, 2013, pp. 580-584.

Scopus Eid


  • 2-s2.0-84891093375

Ro Full-text Url


  • http://ro.uow.edu.au/cgi/viewcontent.cgi?article=2958&context=eispapers

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/1949

Start Page


  • 580

End Page


  • 584

Place Of Publication


  • http://iscit2013.org/content/