Title: What do you think about this photo? A novel approach to opinion and sentiment analysis of photo comments

Authors: Slava Kisilevich; Christian Rohrdantz; Veronica Maidel; Daniel Keim

Addresses: Department of Computer and Information Science, University of Konstanz, P.O. Box 78, 78457 Konstanz, Germany ' Department of Computer and Information Science, University of Konstanz, P.O. Box 78, 78457 Konstanz, Germany ' School of Information Studies, Syracuse University, 343 Hinds Hall, Syracuse, NY 13244-4100, USA ' Department of Computer and Information Science, University of Konstanz, P.O. Box 78, 78457 Konstanz, Germany

Abstract: We propose a practical unsupervised approach to opinion and sentiment analysis of photo comments with a real-valued strength orientation. We extract two types of opinions: opinions that relate to the photo quality and general sentiments targeted towards objects depicted on the photo. Our approach combines linguistic features for part of speech tagging, traditional statistical methods for modelling word importance in the photo comment corpus (in a real-valued scale), and a predefined lexicon for detecting negative and positive opinion orientation. In addition, we apply a semi-automatic photo feature detection method and introduce a set of syntactic patterns to resolve opinion references. The results of our user study among 49 non-expert participants of different ages showed no statistical differences between user evaluation and the algorithm.

Keywords: photo comments; predefined lexicon; negative opinions; positive opinions; sentiment analysis; inter-rater agreement; intraclass correlation coefficient; data mining; photographs; photo quality; depicted objects; speech tagging; modelling; word importance; feature detection; syntactic patterns.

DOI: 10.1504/IJDMMM.2013.053693

International Journal of Data Mining, Modelling and Management, 2013 Vol.5 No.2, pp.138 - 157

Published online: 29 Jul 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article