Lexicon-Based Sentiment Convolutional Neural Networks for Online Review Analysis

Huang, Minghui; Xie, Haoran; Rao, Yanghui; Liu, Yuwei; Poon, Leonard K. M.; Wang, Fu Lee

doi:10.1109/taffc.2020.2997769

Cited by 43 publications

(17 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We would also try to improve the accuracy of our RoBERTa model. New and interesting methods have been proposed to detect emotion [21] and sentiment [22] by using models such LTSM and lexicon-based convolutional neural network. We would also try to explore these models in our future studies.…”

Section: Discussionmentioning

confidence: 99%

“…Imran et al [21] analyzed tweets from six countries for crosscultural polarity and emotion detection using deep learning method. Huang et al [22] presented sentiment convolutional neural networks to analyze the sentiment of sentences with both contextual and sentiment information of sentiment words. Boon-Itt, and Skunkan [23] investigated Twitter posts using sentiment analysis and topic modeling approach to find out the public perception during the COVID-19 pandemic.…”

Section: B Sentiment Analysis and Emotion Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Investigating COVID-19 News Across Four Nations: A Topic Modeling and Sentiment Analysis Approach

Ghasiya

Okamura

2021

IEEE Access

View full text Add to dashboard Cite

Newspapers are very important for a society as they inform citizens about the events around them and how they can impact their life. Their importance becomes more crucial and indispensable in the times of health crisis such as the current COVID-19 pandemic. Since the starting of this pandemic newspapers are providing rich information to the public about various issues such as the discovery of a new strain of coronavirus, lockdown and other restrictions, government policies, and information related to the vaccine development for the same. In this scenario, analysis of emergent and widely reported topics/themes/issues and associated sentiments from various countries can help us better understand the COVID-19 pandemic. In our research, the database of more than 100,000 COVID-19 news headlines and articles were analyzed using top2vec (for topic modeling) and RoBERTa (for sentiment classification and analysis). Our topic modeling results highlighted that education, economy, US, and sports are some of the most common and widely reported themes across UK, India, Japan, South Korea. Further, our sentiment classification model achieved 90% validation accuracy and the analysis showed that the worst affected country, i.e. the UK (in our dataset) also has the highest percentage of negative sentiment.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: B Sentiment Analysis and Emotion Detectionmentioning

confidence: 99%

Investigating COVID-19 News Across Four Nations: A Topic Modeling and Sentiment Analysis Approach

Ghasiya

Okamura

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…tf idf (w, D) = tf (w, D) × log N df (w) + 1 (7) The features that are extracted by TF-IDF from sample documents are shown in Table 10.…”

Section: ) Term Frequencymentioning

confidence: 99%

“…However, with the generation of a large amount of data every day, manual annotation of the data becomes a time-consuming and laborintensive task. So, lexicon-based, also known as a rule-based approach is developed for sentiment analysis [7]. It uses human-crafted rules to detect the sentiments or context of an opinion.…”

Section: Introductionmentioning

confidence: 99%

Determining the Efficiency of Drugs Under Special Conditions From Users’ Reviews on Healthcare Web Forums

et al. 2021

View full text Add to dashboard Cite

Sentiment analysis is the extraction and categorization of sentiments that have been expressed in text data using text analysis techniques. Manifested by earlier studies, sentiment analysis of drug reviews has a large potential for providing valuable insights to assist health-care professionals and companies for evaluating the safety of drugs after it has been marketed. Such insights help safeguard patients and increase their trust in medical companies. The existing systems either follow a lexicon-based approach or a learningbased approach for sentiment analysis in the medical domain. Learning-based techniques require annotated data while lexicon-based techniques tend to be domain-specific which restricts their wide use. This research embarks on a hybrid technique that utilizes both learning-based and lexicon-based approaches to achieve better results. General-purpose sentiment lexicons, such as AFFIN, TextBlob, and VADER, are used for annotating the reviews. Furthermore, several feature engineering techniques, such as term frequency (TF), term frequency-inverse document frequency (TF-IDF), and union of TF and TF-IDF (TF U TF-IDF) have been incorporated for the extraction of useful features. Finally, the learning models including logistic regression (LR), AdaBoost classifier (AB), random forest (RF), extra tree classifier (ETC), and multilayer perceptron (MLP) are used to classify sentiments of the reviews. The performance of the proposed hybrid approach is evaluated using accuracy, precision, recall, and F1-score. Experimental results indicate that the combination of learning-based and lexicon-based approaches provide improved results than their individual use. Moreover, TextBlob has shown promising results giving an accuracy of 96% with MLP when used with TF-IDF and with LR when used with TF U TF-IDF.

show abstract

“…It has got two main approaches namely dictionary and the corpus-based approaches. The authors of Huang et al (2020) have employed the lexicon-based approach for text sentiment classification. The researchers of Baccianella, Esuli, and Sebastiani (2010) have demonstrated the use of WordNet for text sentiment classification in which the words with the same meaning will have a similar polarity.…”

Section: Lexicon Based Approachmentioning

confidence: 99%

Multimodal sentimental analysis for social media applications: A comprehensive review

Chandrasekaran

Nguyen

Hemanth

2021

WIREs Data Min & Knowl

View full text Add to dashboard Cite

The analysis of sentiments is essential in identifying and classifying opinions regarding a source material that is, a product or service. The analysis of these sentiments finds a variety of applications like product reviews, opinion polls, movie reviews on YouTube, news video analysis, and health care applications including stress and depression analysis. The traditional approach of sentiment analysis which is based on text involves the collection of large textual data and different algorithms to extract the sentiment information from it. But multimodal sentimental analysis provides methods to carry out opinion analysis based on the combination of video, audio, and text which goes a way beyond the conventional text-based sentimental analysis in understanding human behaviors. The remarkable increase in the use of social media provides a large collection of multimodal data that reflects the user's sentiment on certain aspects. This multimodal sentimental analysis approach helps in classifying the polarity (positive, negative, and neutral) of the individual sentiments. Our work aims to present a survey of recent developments in analyzing the multimodal sentiments (involving text, audio, and video/image) which involve humanmachine interaction and challenges involved in analyzing them. A detailed survey on sentimental dataset, feature extraction algorithms, data fusion methods, and efficiency of different classification techniques are presented in this work.

show abstract

Lexicon-Based Sentiment Convolutional Neural Networks for Online Review Analysis

Cited by 43 publications

References 25 publications

Investigating COVID-19 News Across Four Nations: A Topic Modeling and Sentiment Analysis Approach

Investigating COVID-19 News Across Four Nations: A Topic Modeling and Sentiment Analysis Approach

Determining the Efficiency of Drugs Under Special Conditions From Users’ Reviews on Healthcare Web Forums

Multimodal sentimental analysis for social media applications: A comprehensive review

Contact Info

Product

Resources

About