To search, Click below search items. |
| All Published Papers Search Service |
|
|
|
Title |
Determining the Semantic Orientation of Opinion Words using Typed Dependencies for Opinion Word Senses and Sentiwordnet Scores from Online Product Reviews |
|
Author |
Teja Santosh |
| Citation |
Vol. 26 No. 2 pp. 77-84 |
|
Abstract |
Opinion word orientation is a sub discipline of text classification concerned with positive or negative association of the opinionated terms. It has a broad range of applications from tracking users’ opinions about products or about political candidates as conveyed in online forums, to customer relationship management to reduce the churn rate. The synonymy relation graph is used to determine the orientation of the adjectives present in the text available in the product reviews data corpus. It considers the minimum path length along with the connected WordNet synsets. The synonymy relation graph limits in determining the number of orientations of the opinion words present in the synonym graph’s minimal path. To evaluate opinion orientation of any adjective from the dataset, the synonymy relation graph of WordNet is replaced with the Sentiwordnet 3.0 scores of the opinion word. These scores are provided to the opinion word by finding the contextual clues surrounding the opinion word to disambiguate its sense. The contextual clues are finalized based on the typed dependencies grammatical relations. The distance between the opinion word and the context insensitive seed term (good/bad) is computed by calculating the difference between these scores. This paper addresses the limitation identified in the synonymy relation graph of WordNet based determination of semantic orientation. This improves the accuracy of the determined opinion word orientations. |
|
Keywords |
Opinion Mining, Text classification, seed terms, opinion word orientation, semantic orientation |
|
URL |
