Multi-aspect sentiment analysis for Chinese online social reviews based on topic modeling and HowNet lexicon

Fu, Xianghua; Guo, Liang; Ye, Guo; Wang, Zhiqiang

doi:10.1016/j.knosys.2012.08.003

Cited by 228 publications

(72 citation statements)

References 30 publications

(30 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…When the document-or sentence-based sentiment analysis is employed, it is not easy to justify which topic ("product" or "service") the sentiments ("good" or "bad") belong to. Hence, many researchers have begun to conduct topic-based sentiment analyses [10][11][12]14].…”

Section: Sentiment Analysismentioning

confidence: 99%

“…As for topic naming, there are two approaches: one is based on the naming process that manually summarizes the meaning of the extracted top words [11,15,16,[50][51][52]. The other approach is based on the naming process that automatically generates the topic meaning based on supervised learning and a word-list [53] (Table 3).…”

Section: Topic-based Sentiment Analysismentioning

confidence: 99%

“…In recent years, an emerging stream of research became important: topic-based or aspect-based sentiment analysis [10][11][12], which refers to the process of identifying product topics for an online store (e.g., product features) and classifying the corresponding sentiments for each topic [13]. The topic-based sentiment analysis approach was also applied to extract tourism-related topics (e.g., hotel services and prices) using online reviews [14][15][16].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Investigating Online Destination Images Using a Topic-Based Sentiment Analysis Approach

Ren

Hong

2017

Sustainability

View full text Add to dashboard Cite

With the development of Web 2.0, many studies have tried to analyze tourist behavior utilizing user-generated contents. The primary purpose of this study is to propose a topic-based sentiment analysis approach, including a polarity classification and an emotion classification. We use the Latent Dirichlet Allocation model to extract topics from online travel review data and analyze the sentiments and emotions for each topic with our proposed approach. The top frequent words are extracted for each topic from online reviews on Ctrip.com. By comparing the relative importance of each topic, we conclude that many tourists prefer to provide "suggestion" reviews. In particular, we propose a new approach to classify the emotions of online reviews at the topic level utilizing an emotion lexicon, focusing on specific emotions to analyze customer complaints. The results reveal that attraction "management" obtains most complaints. These findings may provide useful insights for the development of attractions and the measurement of online destination image. Our proposed method can be used to analyze reviews from many online platforms and domains.

show abstract

Section: Sentiment Analysismentioning

confidence: 99%

Section: Topic-based Sentiment Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Investigating Online Destination Images Using a Topic-Based Sentiment Analysis Approach

Ren

Hong

2017

Sustainability

View full text Add to dashboard Cite

show abstract

“…This technique was introduced by the Guo and Xianghua [13] to discuss about social reviews in Chinese. This technique is just opposite to the supervised learning.…”

Section: Unsupervised Learningmentioning

confidence: 99%

Sentiment Analysis Approach for Resource-Scarce Languages

2017

IJAERD

View full text Add to dashboard Cite

“…Unsupervised approaches also have a long history for SA. Xianghua and Guo [30] presented work in the Chineselanguage domain. Their work used an unsupervised approach to automatically segment Chinese social reviews into aspectsand compute the sentiment expressed in each aspect.…”

Section: A Sentiment Analysis In Genaralmentioning

confidence: 99%

Arabic Sentiment Analysis: A Survey

Assiri¹,

Emam²,

Al-Dossari³

2015

ijacsa

View full text Add to dashboard Cite

Abstract-Most social media commentary in the Arabic language space is made using unstructured non-grammatical slang Arabic language, presenting complex challenges for sentiment analysis and opinion extraction of online commentary and micro blogging data in this important domain. This paper provides a comprehensive analysis of the important research works in the field of Arabic sentiment analysis. An in-depth qualitative analysis of the various features of the research works is carried out and a summary of objective findings is presented. We used smoothness analysis to evaluate the percentage error in the performance scores reported in the studies from their linearly-projected values (smoothness) which is an estimate of the influence of the different approaches used by the authors on the performance scores obtained. To solve a bounding issue with the data as it was reported, we modified existing logarithmic smoothing technique and applied it to pre-process the performance scores before the analysis. Our results from the analysis have been reported and interpreted for the various performance parameters: accuracy, precision, recall and F-score.

show abstract

Multi-aspect sentiment analysis for Chinese online social reviews based on topic modeling and HowNet lexicon

Cited by 228 publications

References 30 publications

Investigating Online Destination Images Using a Topic-Based Sentiment Analysis Approach

Investigating Online Destination Images Using a Topic-Based Sentiment Analysis Approach

Sentiment Analysis Approach for Resource-Scarce Languages

Arabic Sentiment Analysis: A Survey

Contact Info

Product

Resources

About