Morpheme-based derivation of bipolar semantic orientation of Chinese words

Abstract

The evaluative character of a word is called its semantic orientation (SO). A positive SO indicates desirability (e.g. Good, Honest) and a negative SO indicates undesirability (e.g., Bad, Ugly). This paper presents a method, based on Turney (2003), for inferring the SO of a word from its statistical association with strongly-polarized words and morphemes in Chinese. It is noted that morphemes are much less numerous than words, and that also a small number of fundamental morphemes may be used in the modified system to great advantage. The algorithm was tested on 1,249 words (604 positive and 645 negative) in a corpus of 34 million words, and was run with 20 and 40 polarized words respectively, giving a high precision (79.96% to 81.05%), but a low recall (45.56% to 59.57%). The algorithm was then run with 20 polarized morphemes, or single characters, in the same corpus, giving a high precision of 80.23% and a high recall of 85.03%. We concluded that morphemes in Chinese, as in any language, constitute a distinct sub-lexical unit which, though small in number, has greater linguistic significance than words, as seen by the significant enhancement of results with a much smaller corpus than that required by Turney.

Sentiment analysis of Chinese documents: From sentence to document level

“…To the best of our knowledge, there are only a limited number of studies that focus on Chinese sentiment analysis (e.g., Tsou, Yuen, et al, 2005;Yuen, Chan, et al, 2004;Ye, Shi, et al, 2006;Su, Xu, et al, 2008). Yuen et al (2004) presented a method based on Turney and Littman (2003) to determine the semantic polarity of a Chinese word based on its morpheme and its statistical association with strongly polarized words.…”

“…For example, Hatzivassiloglou and McKeown (1997) predicted the semantic orientation of adjectives by analyzing them in pairs conjoined by "and," "or," "but," "either-or," or "neither-nor." Yuen et al (2004) proposed an approach to deriving words' semantic polarity based on morpheme. Knowledge sources such as WordNet have also been used to measure adjectives' semantic polarity (Kamps, Marx, et al, 2004).…”

Sentiment Analysis by Exploring Large Scale Web-based Chinese Short Text

“…Narayanan and et al [9] studied sentiment analysis of conditional sentences with linguistic knowledge. Yuen and et al [10] applied a method based on PMI presented by Turney [8] and morphemes in Chinese, which give high precision and recall in deciding semantic orientation of Chinese words.…”

“…And with polar lexical items found by Yuen [10], Tsou [11] brought out an algorithm exploring the spread, density and intensity of polar lexical items, and classified news articles regarding political figures with good performance. Ku and Chen [12] collected a Chinese sentiment words dictionary called NTUSD, which is widely used nowadays, and determined sentiment polarity of a sentence by identifying sentiment words, negation operators and opinion holders in it.…”

Word sketch lexicography: new perspectives on lexicographic studies of Chinese near synonyms

“…The analysis of users' emotional tendencies (or sentiment) can be used to improve the quality of products and services, which have an important commercial value (Lu et al 路斌等 2007;Xu et al 徐琳宏等 2007;You et al 游彬等 2013;Yuen et al 2004). However, at present, the dominant paradigm of the study on emotion, especially in natural language processing, is only on polarity and does not provide deep insights to our understanding of the emotion content of these words.…”