Abstract
The sentiment polarity of sentiment words often appears inconsistent in different commodity fields, due to the numerous fields involved in online commodity reviews. Traditional methods of manually labeling sentiment polarity are time-consuming and laborious. To solve this problem, this paper proposes a Sentiment Polarity Automatic Calculation Method (SPACM) to calculate the sentiment word polarity in commodity reviews. First, the sentiment words are divided into positive, negative and neutral word sets based on Chinese sentiment word ontology base and the weak tagging information of user’s score. Then, based on the weight of each character in word sets, the sentiment polarity value of sentiment character is obtained by normalization of Gaussian function. The sentiment polarity value of sentiment word composed of characters is obtained by method of cumulative averaging. Finally, the sentiment dictionary with weights is constructed. Based on the characteristic of the distribution of sentiment word polarity values in three word sets, the concept of distinguishing the threshold is proposed as the basis of division to re-divide the polarity of sentiment words. The experimental results demonstrate the effectiveness of the proposed method.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.