Benefits of using ranking skip-gram techniques for opinion mining approaches
- 1 November 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-10
Abstract
This paper presents an opinion mining approach in the domain of Social TV using two different contexts: Twitter user messages for Spanish and English, as well as movie reviews. The main goal of this paper is to study the benefits of opinion mining approaches using ranking skip-gram techniques for processing user feedbacks. To carry out this study it is described a system based on supervised machine learning and text categorisation techniques. This system has been evaluated on user messages obtained from Twitter and Amazon users' reviews. Results demonstrate that the use of ranking skip-grams techniques provide suitable opinion mining results independently of the language and scenario of application. The paper also presents information about business benefits of these technologies which are part of an advanced digital media delivery platform currently under development in the framework of the EU-funded project SAM - Socialising Around Media.Keywords
This publication has 10 references indexed in Scilit:
- SemEval-2014 Task 9: Sentiment Analysis in Twitter2014
- GPLSI: Supervised Sentiment Analysis in Twitter using Skipgrams2014
- Text summarisation in progress: a literature reviewArtificial Intelligence Review, 2011
- LIBSVMACM Transactions on Intelligent Systems and Technology, 2011
- Evaluating EmotiBlog Robustness for Sentiment Analysis TasksLecture Notes in Computer Science, 2011
- The WEKA data mining softwareACM SIGKDD Explorations Newsletter, 2009
- Opinion Mining and Sentiment AnalysisFoundations and Trends® in Information Retrieval, 2008
- Summarizing spoken and written conversations2008
- A sentimental education2004
- Machine learning in automated text categorizationACM Computing Surveys, 2002