Lexicon based Chinese language sentiment analysis method

Chen, Jinyan; Becken, Susanne; Stantić, Bela

doi:10.2298/csis181015013c

Cited by 15 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They proposed a Recurrent Neural Network (RNN)-based technique in their study that can be generalised to different languages, particularly resource-constrained languages that lack data resources and have less useful data for SA purposes. Chen et al (Chen, Becken, and Stantic, 2019) proposed a lexicon-based approach for SA of Chinese social media posts. They developed a comprehensive process for capturing web posts and a lexicon algorithm for SA in their study (Sehar et al, 2021).…”

Section: Literature Reviewmentioning

confidence: 99%

A Hybrid Dependency-Based Approach for Urdu Sentiment Analysis

Sehar

Kanwal

Dashtipur

et al. 2022

Preprint

View full text Add to dashboard Cite

In this era of internet, it is evident that social media is one of the biggest platforms acting as a source of producing a huge amount of raw data on a daily basis that contains the opinion of people from different races, cultures, and age groups on a wide range of topics. Data that is produced on the social media platforms could be utilised by businesses to extract information for improving their services and to reach a wider set of audiences based on users' opinions being shared on these social media sites. In order to utilise this huge amount of unstructured data generated continuously on social media, a deep understanding of Natural Language Processing (NLP) is vital. Most of the approaches proposed so far for sentiment analysis (SA) are based on word co-occurrence frequencies that are inefficient in practical cases. Considering this research gap, this paper proposes a framework for concept-level SA for better SA. We developed our Urdu language dataset by collecting from YouTube, which comprises talks and reviews on different topics like movies, political, and commercial products. Further dataset was integrated with language rules and Deep Neural Networks (DNN) to optimise the polarity detection. For SA, when a predefined rule is triggered, the framework enables the sentiments to flow from words to concepts based on dependency relations among different words of a sentence on the basis of Urdu language grammatical rules. When any of the predefined patterns is not triggered, the framework switches to its sub-symbolic counterpart and passes data to DNN for performing the classification of input sentence. The proposed framework outperforms state-of-the-art approaches, including Long short-term memory (LSTM), Convolutional Neural Network (CNN), State Vector Machine (SVM), Linear Regression (LR), and Multilayer Perceptrons (MLP), with a margin of 6–7%, respectively, when employed on our Urdu dataset.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

A Hybrid Dependency-Based Approach for Urdu Sentiment Analysis

Sehar

Kanwal

Dashtipur

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Currently, emotional intensity or sentimental orientation has attracted a growing attention from the academia. The calculation of emotional intensity or sentimental orientation is usually realized by constructing an emotional intensity dictionary (Yu et al, 2017;Elsaid et al, 2018;Chen et al, 2019).…”

Section: Sentiment Analysismentioning

confidence: 99%

Dynamic Measurement and Evaluation of Hotel Customer Satisfaction Through Sentiment Analysis on Online Reviews

Zhou

Liao

2021

Journal of Organizational and End User Computing

View full text Add to dashboard Cite

Both researchers and practitioners have attached great importance to the measurement and evaluation of hotel customer satisfaction. However, there are several problems in the dimensions, methods and conclusions. Thus, it is urgent to standardize the theories, methods, and techniques. The purpose of this study is to propose a dynamic measurement and evaluation framework for hotel customer satisfaction through sentiment analysis on online reviews. The framework consists of five steps: (1)The corpus is obtained from online review sites; (2)From the perspective of managers, the useful texts are recognized; (3)Based on the useful texts, a three-layer index system is created; (4)The center term-based short sentence sentimental orientation (CTSSSO) algorithm is developed to compute emotional intensity, then dynamically measure the customer satisfaction; (5)The dynamic important performance competitor analysis (DIPCA) is adopted for dynamic evaluation of customer satisfaction.The feasibility of our framework was demonstrated through a case study on the online reviews of two five-star hotels.

show abstract

“…For each post, the number of positive and negative words were counted, respectively. Because NTUSD contains no detailed polarity strength of each word, counted weights were assigned ('+1' for each positive word and '-1' for each negative word) (34), which yielded positive and negative sentiment scores for each post.…”

Section: Sentiment Analysismentioning

confidence: 99%

Understanding the landscape and propagation of COVID-19 misinformation and its correction on Sina Weibo

Yang

Luo

et al. 2021

Glob Health Promot

View full text Add to dashboard Cite

The prevalence of health misinformation on social media could significantly influence individuals’ health behaviors. To examine the prevalent topics, propagation, and correction of coronavirus disease 2019 (COVID-19) misinformation, automated content analyses were conducted for posts on Sina Weibo, which is China’s largest microblogging site. In total, 177,816 posts related to COVID-19 misinformation during the COVID-19 outbreak in China were analyzed. The structural topic modeling identified 23 valid topics regarding COVID-19 misinformation and its correction, which were further categorized into three general themes. Sentiment analysis was conducted to generate positive and negative sentiment scores for each post. The zero-inflated Poisson model indicated that only the negative sentiment was a significant predictor of the number of comments (β = 0.003, p < 0.001) but not reposts. Furthermore, users are more prone to repost and comment on information regarding prevention/treatment (e.g., traditional Chinese medicine preventing COVID) as well as potential threats of COVID-19 (e.g., COVID-19 was defined as an epidemic by World Health Organization). Health education and promotion implications are discussed.

show abstract

Lexicon based Chinese language sentiment analysis method

Cited by 15 publications

References 18 publications

A Hybrid Dependency-Based Approach for Urdu Sentiment Analysis

A Hybrid Dependency-Based Approach for Urdu Sentiment Analysis

Dynamic Measurement and Evaluation of Hotel Customer Satisfaction Through Sentiment Analysis on Online Reviews

Understanding the landscape and propagation of COVID-19 misinformation and its correction on Sina Weibo

Contact Info

Product

Resources

About