Sentiment Classification Using Machine Learning Techniques with Syntax Features

Zou, Huang; Tang, Xinhua; Xie, Bin; Liu, Bing

doi:10.1109/csci.2015.44

Cited by 53 publications

(20 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pang et al (2002) used Naive Bayes, support vector machine (SVM) and Maximum Entropy Learning Classifier to classify the emotions of movie reviews, and finally proved that SVM has the best classification effect. Zou et al (2015) considered the complex syntactic relationship in the text, combine the position of words, the dependence/grammar relationship between words and the part-of-speech characteristics, and effectively improved the performance of emotional classification to 86 per cent. Rao et al (2016) used potential topics, emotional tags and readers’ emotional scores to generate topic features and proposed a topical classification method based on topic-level maximum entropy.…”

Section: Related Workmentioning

confidence: 99%

Emotional communication analysis of emergency microblog based on the evolution life cycle of public opinion

Zhang

Jie

Boncella

2020

IDD

View full text Add to dashboard Cite

Purpose Microblogging is an important channel used to disseminate online public opinion during an emergency. Analyzing the features and evolution mechanism of online public opinion during an emergency plays a significant role in crisis management. Design/methodology/approach This paper uses the event of Hurricane Irma and combines it with the life cycle of online public opinion evolution to understand the effect of different types of emotional (joy, anger, sadness, fear, disgust) microblogs (tweets) on information dissemination. The research was performed in the context of Hurricane Irma by using tweets associated with that event. Findings This paper demonstrates that negative emotional information has a greater communication effect, and further, the target audience that receives more exposure to negative emotional microblogs has a stronger tendency to retweet. Meanwhile, emotions expressed in tweets and the life cycle of public opinion evolution exert interactive effects on the retweeting behavior of the target audience. Research limitations/implications For future research, a professional dictionary and the context should be taken into consideration to make the modeling in the text more normative and analyzable. Practical implications This paper aims to reveal how the emotions of a tweet affect its virality in terms of diffusion volume in the context of an emergency event. Social implications The conclusion made in this paper can shed light on the real-time regulation and public opinion transmission, as well as for efficient intelligence service and emergency management. Originality/value In this study, Hurricane Irma is taken as an example to explore the factors influencing the information dissemination during emergencies on the social media environment. The relationship between the sentiment of a tweet and the life cycle of public opinion and its effect on tweet volume were investigated.

show abstract

Section: Related Workmentioning

confidence: 99%

Emotional communication analysis of emergency microblog based on the evolution life cycle of public opinion

Zhang

Jie

Boncella

2020

IDD

View full text Add to dashboard Cite

show abstract

“…By comparing the performance of Naive Bayes (NB), Maximum Entropy (ME) and Support Vector Machine (SVM) combined with different features on emotion classification, they find that the accuracy of SVM combined with UNIGRAMS features could reach 82.9% [9]. ZOU and TANG et al take into account the complex syntactic relationships in the text, which combine word positions, dependence or grammatical relations between words and part-of speech characteristics, effectively improving the emotional classification performance [10]. Although machine learning method achieves good results, it requires a large number of manual annotation data sets to train the model, and the high-quality data sets cost a lot of time and labor.…”

Section: ) Machine Learning Methodsmentioning

confidence: 99%

Sentiment Analysis About Investors and Consumers in Energy Market Based on BERT-BiLSTM

et al. 2020

View full text Add to dashboard Cite

With the rapid development of social media, the number of online comments has exploded, and more and more people are willing to express their attitudes and feelings on the Internet. Under the influence of a series of major events all over the world, production order is facing a serious challenge, which severely impact on energy market. In 2020, a large number of investors' and consumers' comments related to social events began to appear on the Internet from China. However, the style and quality of online comments vary greatly, making it difficult to accurately extract users' views and tendencies. Based on the investors' and consumers' statements published on Chinese Internet, in this paper, we use statistical methods to classify the sentiment orientation of the Netizens firstly, and then use Bidirectional Encoder Representations from Transformer-Bidirectional Long Short Term Memory (BERT-BiLSTM) which is the combination forecasting method of Bidirectional Encoder Representations from Transformer (BERT) and Bidirectional Long Short Term Memory (BiLSTM), to model and forecast the sentiment orientation of users' statements, as well as being compared with its based models, BERT and BiLSTM. Among them, the accuracy and recall，which represent the predictive abilities on the overall samples and on the focus(the samples of Label 1) respectively, of BERT-BiLSTM model are 0.8620 and 0.7078 respectively, which are superior to those of BERT model (0.8559 and 0.5576) and LSTM model (0.7775 and 0.0747). The research results can accurately predict the sentiment orientation of Internet users during the social events so as to provide technical support for grasping the energy market trend. INDEX TERMS sentiment analysis, combination model, BERT-BiLSTM, energy market, investors and consumers.

show abstract

“…They used NB, Maximum Entropy, and SVM classifiers to achieve a two-class classification. Tripathy et al [6] and Zou et al [7] furthered the work of Pang et al [5] by adding TF-IDF, POS tagging, and Stochastic Gradient Descent (SGD) in order to improve the accuracies. Ukhti Ikhsani Larasati et al [8] developed the work of Tripathy et al [6] and used the chi-squared method of feature selection along with the already proposed SVM classifier.…”

Section: Literature Surveymentioning

confidence: 99%

JUMRv1: A Sentiment Analysis Dataset for Movie Recommendation

et al. 2021

View full text Add to dashboard Cite

Nowadays, we can observe the applications of machine learning in every field, ranging from the quality testing of materials to the building of powerful computer vision tools. One such recent application is the recommendation system, which is a method that suggests products to users based on their preferences. In this paper, our focus is on a specific recommendation system called movie recommendation. Here, we make use of user reviews of movies in order to establish a general outlook about the movie and then use that outlook to recommend that movie to other users. However, a huge number of available reviews has baffled sophisticated review systems. Consequently, there is a need to find a method of extracting meaningful information from the available reviews and use that in classifying a movie review and predicting the sentiment in each one. In a typical scenario, a review can either be positive, negative, or indifferent about a movie. However, the available research articles in the field mainly consider this as a two-class classification problem—positive and negative. The most popular work in this field was performed on Stanford and Rotten Tomatoes datasets, which are somewhat outdated. Our work is based on self-scraped reviews from the IMDB website, and we have annotated the reviews into one of the three classes—positive, negative, and neutral. Our dataset is called JUMRv1—Jadavpur University Movie Recommendation dataset version 1. For the evaluation of JUMRv1, we took an exhaustive approach by testing various combinations of word embeddings, feature selection methods, and classifiers. We also analysed the performance trends, if there were any, and attempted to explain them. Our work sets a benchmark for movie recommendation systems that is based on the newly developed dataset using a three-class sentiment classification.

show abstract

Sentiment Classification Using Machine Learning Techniques with Syntax Features

Cited by 53 publications

References 3 publications

Emotional communication analysis of emergency microblog based on the evolution life cycle of public opinion

Emotional communication analysis of emergency microblog based on the evolution life cycle of public opinion

Sentiment Analysis About Investors and Consumers in Energy Market Based on BERT-BiLSTM

JUMRv1: A Sentiment Analysis Dataset for Movie Recommendation

Contact Info

Product

Resources

About