A Sentiment Classification from Review Corpus using Linked Open Data and Sentiment Lexicon

Suwanpipob, Worapoj; Arch-int, Ngamnij; Wattana, Monlica

doi:10.1109/icitee53064.2021.9611898

Cited by 4 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…14,23,24 The lexicon approach uses a dictionary of positive and negative terminologies to assess and determine the polarity of an opinion. This can be further classified as dictionary-based 25,26 and corpus-based 27,28 approaches. The dictionary approach uses a dictionary of opinionated words with established guidelines for sentiment analysis, while corpus based methods use statistical analysis of large collections of written or spoken data (corpora) to determine the polarity of text.…”

Section: Related Workmentioning

confidence: 99%

Sentiment analysis on social media tweets using dimensionality reduction and natural language processing

Omuya

Okeyo

Kimwele

2022

Engineering Reports

View full text Add to dashboard Cite

Social media has been embraced by different people as a convenient and official medium of communication. People write or share messages and attach images and videos on Twitter, Facebook and other social media platforms. It therefore generates a lot of data that is rich in sentiments. Sentiment analysis has been used to determine the opinions of clients, for instance, relating to a particular product or company. Lexicon and machine learning approaches are the strategies that have been used to analyze these sentiments. The performance of sentiment analysis is, however, distorted by noise, the curse of dimensionality, the data domains and the size of data used for training and testing. This article aims at developing a model for sentiment analysis of social media data in which dimensionality reduction and natural language processing with part of speech tagging are incorporated. The model is tested using Naïve Bayes, support vector machine, and K‐nearest neighbor algorithms, and its performance compared with that of two other sentiment analysis models. Experimental results show that the model improves sentiment analysis performance using machine learning techniques.

show abstract

Section: Related Workmentioning

confidence: 99%

Sentiment analysis on social media tweets using dimensionality reduction and natural language processing

Omuya

Okeyo

Kimwele

2022

Engineering Reports

View full text Add to dashboard Cite

show abstract

“…After combining the scores of all the words, it uses the mathematical and statistical methods to determine the final scores to identify the sentiment of the text (Taboada et al, 2011), as shown in Figure 3. The scores and classifications of texts depend on the vocabulary in the dictionary for the analysis and classification of English sentiments (Suwanpipob, 2019). Jaihuek and Mungsing (2018) used an automatic scoring program to create a dictionary for the keywords of answers.…”

Section: Lexicon-based Approach (Lb Approach)mentioning

confidence: 99%

“…For example, messages are classified as the expression of opinions to the Thai government, whether positive or negative. Text classification methods are divided into two methods (Suwanpipob, 2019), lexicon-based approach and machine learning approach.…”

Section: Techniques For Classifying Text and Evaluating Performancementioning

confidence: 99%

See 1 more Smart Citation

A Survey of Automatic Text Classification Based on Thai Social Media Data

Tanantong

Parnkow

2022

International Journal of Knowledge and Systems Science

View full text Add to dashboard Cite

In the digital age, the information on social media, such as Facebook, Twitter, and Instagram, is increasing rapidly. Therefore, it has led to studies and researches on social media analytics to extract useful models or knowledge from the data. One of the most interesting topics in social media analytics is text classification on social media data. However, since social media data has a diverse and complex data structure, text analysis and classification are considered a challenging issue that requires a specific technique to implement. The objective of this review paper is to collect and review research related to the automatic classification of Thai text on social media by presenting and explaining the process of text classification on various issues. These include data collection and data sources, amount of data and data preparation for research, feature extraction methods, text classification automated modeling methods, efficacy evaluation and measurement methods, the results of text classification, and summary of the overall trend of research on the topic.

show abstract

“…The existing business researches of eWOM commercial value mainly discuss how consumers make decisions by reading eWOM text by qualitative analysis, since obtaining sentiment value from a large amount of texts may be difficult for economics or business researchers for the computer programming techniques requirement, so related literatures utilized the polarity of "positive" and "negative" of eWOM content to quantify the sentiment of eWOM text [9]. And computer science researchers did not focus on the commercial problem about sentiment value; they prioritized optimizing the algorithm [10][11] and the base corpus [12][13][14][15] of sentiment analysis method to enhance the calculation accuracy of sentiment value, and were enthusiastic about technical application [16][17]. Therefore, the impact of eWOM textual sentiment value on business causality is a cross-cutting issue that remains unaddressed in existing literature.…”

Section: Introductionmentioning

confidence: 99%

Online Evaluation Information Cascade and Its Impact on Consumer Decision Making: Analyzing Movie Reviews Using Sentiment Corpus

Tuo

2024

IEEE Access

View full text Add to dashboard Cite

User-generated content on self-media platforms significantly influences the market. In the era of Web 2.0, consumers make purchasing decisions based on electronic word-of-mouth (eWOM) of these platforms. This research illustrates how sentiment value in eWOM content guides consumers' behavior by empirical study based on the causality approach. The research calculates the sentiment value of 160,000 textual film reviews using sentiment analysis program which is based on the sentiment corpus and addressing sarcasm. It also measures the complexity of information by calculating entropy to capture the information cascade process of eWOM into reputation signal. The findings illustrate the causal relationship between positive eWOM content and consumers' decision-making processes, as well as the extent to which consumers rely on eWOM textual information when making consumption decisions. When the eWOM information conveys a clear reputation signal, it will have a lasting impact on future box office performance. This article is the initial empirical literature that quantifies the commercial value of online text sentiment information through a causal and dynamic perspective. It is also the first literature to empirically demonstrate the formation process of sentiment information cascade during the eWOM spreading process among the netizens and capture the required time lag for the formation of online consumer reputation signal.INDEX TERMS Sentiment analysis; information cascade; entropy; user-generated content; Chinese text; movie reviews HONG TUO received the B.S. degree in information management and information system from Beijing University of Chemical and Technology, Beijing, in 2019. She is currently pursuing the Ph.D. degree in economics at

show abstract

A Sentiment Classification from Review Corpus using Linked Open Data and Sentiment Lexicon

Cited by 4 publications

References 16 publications

Sentiment analysis on social media tweets using dimensionality reduction and natural language processing

Sentiment analysis on social media tweets using dimensionality reduction and natural language processing

A Survey of Automatic Text Classification Based on Thai Social Media Data

Online Evaluation Information Cascade and Its Impact on Consumer Decision Making: Analyzing Movie Reviews Using Sentiment Corpus

Contact Info

Product

Resources

About