Research on building Chinese basic semantic lexicon

Liu, Weiping; Zhu, Yanhui; Li, Chun-Liang; Huazheng, Xiang; Wen, Zhiqiang

doi:10.3724/sp.j.1087.2009.02875

Cited by 18 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dictionary and rule-based method refers to the division of sentiment polarity into different granularities based on the sentiment polarity of the sentiment words provided by various sentiment dictionaries [26]. Using the HowNET emotional word set as a benchmark, Liu et al [27] proposed a method for calculating the emotional weights of Chinese emotional words, and results showed that this method is helpful in enhancing the effect of emotion classification in the Chinese corpus. The emotion categorization of text was successfully realized when Xu et al [28] developed an extended sentiment lexicon encompassing fundamental sentiment words, scene sentiment words, and multimeaning sentiment words.…”

Section: Sentiment Analysis Of Online Qanda Communitiesmentioning

confidence: 99%

Exploring the New Energy Vehicle Industry’s Progress Path under the Carbon Peaking and Carbon Neutrality Goals: Evidence from Online Q&A Community’s Emotional Analysis

Xu,

Liu,

Wang

et al. 2024

Pol. J. Environ. Stud.

View full text Add to dashboard Cite

The automotive industry's low-carbon transformation is crucial to a nation's ability to fulfill its "Carbon Peaking and Carbon Neutrality" (CPDN) commitment. However, China's automotive industry still has a number of issues that have sparked debate. Based on the fact that people use social Q&A platforms to get information, solve problems, and aid in decision-making, negative answers in massive amounts of information typically have a higher degree of information perception and are easier to spread. This work constructed the algorithm of emotion calculation and classification, negative network construction for social Q&A platforms, and carried out empirical research with Zhihu. The 175 questions and 5220 corresponding answers for new energy automobiles were organized as a database to search the development path for the new energy automobile industry. The new energy vehicle industry's development path primarily entails: resolving the issue of charging difficulty and popularizing charging heaps; attending to the battery safety issue and the head brand of new energy vehicles concentrating notably on quality control. The empirical findings also demonstrate that algorithms developed can more effectively complete the task of sentiment analysis, aid users in making decisions, and contribute to realizing the CPDN goal.

show abstract

Section: Sentiment Analysis Of Online Qanda Communitiesmentioning

confidence: 99%

Exploring the New Energy Vehicle Industry’s Progress Path under the Carbon Peaking and Carbon Neutrality Goals: Evidence from Online Q&A Community’s Emotional Analysis

Xu,

Liu,

Wang

et al. 2024

Pol. J. Environ. Stud.

View full text Add to dashboard Cite

show abstract

“…Liu built the Chinese basic sentiment lexicon by calculating semantic similarity between seed words and the sentiment words in HowNet [18] . Xu built the affective lexicon ontology which describe a Chinese word or phrase from different angles, including the information of the part of speech, sentiment category, sentiment strength, polarity [19] . Taiwan University has finished the construction of Chinese sentiment lexicon named NTUSD, which include 2812 positive words and 8276 negative words.…”

Section: Related Workmentioning

confidence: 99%

A Method of Building Chinese Sentiment Lexicon Based on Semantics

Jiang

Yang

Zhou

2014

AMM

View full text Add to dashboard Cite

A method was proposed to build a Chinese sentiment lexicon based on semantics. Sentiment intensity of the word was automatically calculated by decomposing it into multiple English semantic units (Esu). A lexicon proofreading method was used to optimize the sentiment intensity of words. The proposed lexicon was applied to the task of sentiment analysis, in which the method of support vector machine was used to build the sentiment classifier. The experiment results shown that the built sentiment lexicon was more effective than the general polar sentiment lexicon.

show abstract

“…On the basis of HowNet, there are many researches on constructing a specific sentiment dictionary. Like Liu Weiping et al [3], based on HowNet sentiment words set, he used its sememe to calculating the similarity between two words. And then based on the difference of average similarity between words and positive and negative seed words, he determined the trend of sentiment words in order to get a sentiment dictionary.…”

Section: Introductionmentioning

confidence: 99%

“…Using the BSL in paper [3] as seed word set, we select word w from BSL and calculate the PMI value between w and others in BSL in the hotel review corpus to get its SO new . Compared the SO new and word w's SO value in BSL, if they have the same sign, then save w into Hotel Review Sentiment Lexicon(HRSL).…”

Section: Introductionmentioning

confidence: 99%

Research on Building a Chinese Sentiment Lexicon Based on SO-PMI

Yang

Lin

Zhou

et al. 2012

AMM

View full text Add to dashboard Cite

Considering user behavior, this paper has built a Chinese sentiment lexicon based on improved SO-PMI algorithm. Sematic lexicons were used to classify the sentiment of the collected Chinese hotel reviews. The experiment has compared the feature extraction between CHI and sentiment lexicons to find out different classification performances. The results indicate that feature extraction based on sentiment lexicon gains higher F1. The performance of classification method “Basic Semantic Lexicon + BOOL + NB” gains 92.40% of F1. Based on different sentiment lexicons, the experimental results shows that (SO-A) and (SO-P) is slightly better than NB classifier. Therefore, it would be effective to use ((SO-A) and (SO-P) as text sentiment classifiers. The experiment also finds out the method “Hotel Reviews Semantic Lexicon using improved SO-PMI algorithm +((SO-A)” gains the highest F1 which is 92.84%. The results reveal that improved SO-PMI does more effective on weight calculation and sentiment lexicon building.

show abstract

Research on building Chinese basic semantic lexicon

Cited by 18 publications

References 0 publications

Exploring the New Energy Vehicle Industry’s Progress Path under the Carbon Peaking and Carbon Neutrality Goals: Evidence from Online Q&A Community’s Emotional Analysis

Exploring the New Energy Vehicle Industry’s Progress Path under the Carbon Peaking and Carbon Neutrality Goals: Evidence from Online Q&A Community’s Emotional Analysis

A Method of Building Chinese Sentiment Lexicon Based on Semantics

Research on Building a Chinese Sentiment Lexicon Based on SO-PMI

Contact Info

Product

Resources

About