Year of Publication: 2013
Page Numbers: 66-71
Authors: Miguel Arcilla, Antonn Esquivel, Celina Quiros, Karina Velasco, Charibeth Cheng
Conference Name: The Second International Conference on Digital Enterprise and Information Systems (DEIS2013)
- Malaysia


As the Internet continues to expand into one of the largest sources of information in the world, more and more applications are being created that are able to extract and make use of valuable knowledge obtained from it. Opinion Mining (OM) and Sentiment Analysis (SA) focus on the subjective elements of text, and the inherent opinions of the writer rather than the contents of their message. The subjective and opinionated nature of the Internet makes it a prime source of data for OM and SA applications. Sentiment Lexicons are databases that store polarity scores of words, and are used by many SA applications as a standard data resource. However, one of the main limitations of modern sentiment lexicons is that they do not take the context of the word into account, and how the polarity of a word can change depending on what it is describing. As certain words may have different opinion orientations when pertaining to different objects, applications that use standard sentiment lexicons may not able to accurately identify the opinion content of a certain text. This research addresses this issue through the creation of a lexicon builder that extract word pairs instead of individual opinionated words. FeLex Builder is a feature-descriptor-based lexical resource builder that is created through an automated extraction of word pairs present in texts and a semi-supervised polarity scoring process. We tested FeLex Builder on online product reviews. Reviews from six different product categories on Amzon were gathered. Evaluation shows a 75.02% accuracy performance of the Felex Builder in extracting word pairs.