标题：Automatically Collect the Adjectives and Calculate Their Sentiment Intensity in the Sentiment Analysis
作者：Wang, Hui; Ji, Xiaohong; Ma, Jun
作者机构：[Wang, Hui; Ma, Jun] Shandong Univ, Sch Comp Sci & Technol, Jinan 250101, Peoples R China.; [Wang, Hui] Tianjin Univ Sci & Technol, Coll Comp Sci & 更多
会议名称：3rd Asian Pacific Conference on Mechanical Components and Control Engineering (ICMCCE)
会议日期：SEP 20-21, 2014
来源：MECHANICAL COMPONENTS AND CONTROL ENGINEERING III
关键词：sentiment analysis; opinion mining; sentiment intensity; synonym;; antonym; WordNet
摘要：In order to automatically expand high quality polarity adjectives as much as possible by using the WordNet, three types of query strings are used in this study. Among them, the third type of query string is the most important. Besides 'synonym' and 'antonym' relations, we also use 'similar to' and 'also see' relations of the WordNet. In fact, the last two relations are more important than the first two ones. With the help of the newly proposed method, we can calculate the sentiment intensity of those expanded adjectives exactly. Abundant experiments demonstrate that our improved POAE algorithm is very effective in expanding and ranking adjective seed list in the sentiment analysis.