Mining the Sentiment Expectation of Nouns Using Bootstrapping Method

Proceedings of the 5th International Joint Conference on Natural Language Processing, pages 1423–1427, Chiang Mai, Thailand, November 8 – 13, 2011. c⃝2011 AFNLP Mining the Sentiment Expectation of Nouns Using Bootstrapping Method Miaomiao Wen Language Technologies Institute Carnegie Mellon University mwen@andrew.cmu.edu Yunfang Wu Key Laboratory of Computational Linguistics (Peking University) Ministry of Education, China wuyf@pku.edu.cn Abstract We propose an unsupervised bootstrapping method to generate a new type of affect knowl- edge base: the sentiment expectation of nouns (e.g., “high salary” is desirable while “high price” is usually undesirable, because peo- ple have opposite sentiment expectation to- wards “salary” and “price”). A bootstrapping framework is designed to retrieve patterns that might be used to express complaints from the Web. The sentiment expectation of a noun could be automatically predicted with the out- put patterns. We evaluate the retrieved pat- terns and show that our method yields good results. Also, they are applied to improve both sentence and document level sentiment analy- sis results. 1 Introduction In recent years, sentiment analysis has attracted con- siderable attention in the NLP community due to its wide applications. The task is mining positive and negative opinions from text and an in-depth review of its literature can be found in Pang and Lee (2008). Previous work on this problem falls into three groups: opinion mining of documents, senti- ment classification of sentences and polarity predic- tion of words. Sentiment analysis both at document and sentence level rely heavily on word level. The most frequently explored task at the word level is to determine the sentiment orientation (SO) of words or word senses in the lexicon. While adjec- tives and verbs are often considered, the sentiment classification of nouns still poses a challenge. This paper aims at identifying people’s sentiment expec- tation towards a noun, even though the noun itself does not carry polarity. We propose three categories of sentiment expectation (SE) of nouns: positive ex- pectation nouns (Pn), negative expectation nouns (Nn) and neutral. For example, “ó]|salary” is a Pn, as “high salaries” is desirable for most people. Also, the noun “d‚|price” describes an object that is generally neutral, but it is a Nn, as most people in most cases expect that the product prices become lower. There are several significances lying in this study. First, the SE of noun reflects world knowledge about an object, which is not readily available in existing semantic resources. This knowledge is useful in de- termining the context dependent SO of adjectives or verbs. For example, “high salary” is desirable while “high price” is undesirable. Also, “receive money” will probably impart positive state onto its patient while “receive hepatitis” will impart negative state onto its patient. Second, our method requires very little human supervision. We introduce an unsupervised bootstrapping ap- proach. Our system is initialized with a very small seed set of nouns, and then iterates between (a) re- trieving a set of complaint patterns (CPs) - lexico- syntactic patterns such as “<n> is a little a” 1 that tend …

Content truncated to 500 words