Sentiment words are employed to compute the tendency of a sentence, and then a document. To detect sentiment words in Chinese documents, a Chinese sentiment dictionary is indispensable. However, a small dictionary may suffer from the problem of coverage. A method to learn sentiment words and their strengths from multiple resources is developed in this task.

First, two sets of sentiment words, General Inquirer1 (GI) and Chinese Network Sentiment Dictionary2 (CNSD), are col-lected. The former is in English and we translate those words into Chinese. The latter, whose sentiment words are collected from the Internet, is in Chinese. Table 1 shows the statistics of the revised dictionaries. Words from these two resources form the “seed vocabulary” in the opinion dictionary. These qualified seeds are collected in National Taiwan University Sentiment Dictionary (NTUSD).

Please cite the following paper if you use this dictionary:

Lun-Wei Ku and Hsin-Hsi Chen (2007). Mining Opinions from the Web: Beyond Relevance Retrieval. Journal of American Society for Information Science and Technology, Special Issue on Mining Web Resources for Enhancing Information Retrieval, 58(12), pages 1838-1850.