Prabhat Verma

Bio: Prabhat Verma is an academic researcher. The author has contributed to research in topics: Sentiment analysis & The Internet. The author has an hindex of 1, co-authored 2 publications receiving 1 citations.

Sentiment analysis of covid-19 epidemic using machine learning algorithms ontwitter -

Abstract: As we know, On February 11, 2020, the World Health Organization declared the official name for the illness that is causing the 2019 novel corona virus episode, first recognized in Wuhan China. More than 216 countries are influenced so far, raising worries of broad dread and expanding tension in people exposed to the danger of the infection. In the 20th century, internet user's who are using social network platforms growing exponentially and getting benefited in the form of information gathering coming from all over the world by using the social network platform like twitter. In the current scenario, many researchers/scientists are working on sentiments of text on social network data shared by internet or social network users. In the form of text (tweets) on the twitter platform, people from all over the world are sharing the challenges of this COVID 19 epidemic in their feeling or opinions. Tweets in the form of text shared on twitter, we extracted the sentiments of the text (tweets) and analyze these sentiments by using the Machine learning algorithm. We can predict the positive, negative, or neutral sentiments (emotions) of the people affected by the COVID 19 epidemic. From, our analyzed sentiment of textual data shared on twitter. We can protect our friends, relatives, and followers on social networks from their depressive or negative behaviour using some preventive measures for which working class peoples are being negative.

Sentiment analysis using machine learning techniques on twitter: a critical review

Abstract: Social web for Social applications are developing an exponential rate over the internet with the growing Internet communities. Users are increasing every second to use the social applications on Social platforms like Twitter, Facebook, etc. Users are sharing their feeling or opinion about any person, product in the form of images or text on the social networks. Sentiment analysis has gained a lot of popularity in the research field of Natural language processing (NLP). Through it, the hidden sentiment in the text can be well extracted. This can assist companies, organizations, or users to make a useful conclusion to achieve their objective. The millions of data on the social network which has shared by the users will get certainly brings more opportunities and challenges to the sentiment analysis. In this paper, we will analyze the various Existing methods, techniques, and approaches for sentiment analysis, like Support Vector Machine, Naive Bayes, and KNN. In this paper, we have adopted a step by step literature review process to identify areas well focused by researchers for sentiment analysis in different fields. We have also tried to identify the best-used sentiment analysis techniques to find research gaps from the previous research, which can further be extended in future research work. We will also discuss and explore new development trends of sentiment analysis. corresponding author 2010 Mathematics Subject Classification. 68T09, 62R07.

Machine learning techniques for emotion detection and sentiment analysis: current state, challenges, and future directions

Abstract: Emotion detection and Sentiment analysis techniques are used to understand polarity or emotions expressed by people in many cases, especially during interactive systems use. Recognizing users’ emotions is an important topic for human–computer interaction. Computers that recognize emotions would provide more natural interactions. Also, emotion detection helps design human-centred systems that provide adaptable behaviour change interventions based on users’ emotions. The growing capability of machine learning to analyze big data and extract emotions therein has led to a surge in research in this domain. With this increased attention, it becomes essential to investigate this research area and provide a comprehensive review of the current state. In this paper, we conduct a systematic review of 123 papers on machine learning-based emotion detection to investigate research trends along many themes, including machine learning approaches, application domain, data, evaluation, and outcome. The results demonstrate: 1) increasing interest in this domain, 2) supervised machine learning (namely, SVM and Naïve Bayes) are the most popular algorithms, 3) Text datasets in the English language are the most common data source, and 4) most research use Accuracy to evaluate performance. Based on the findings, we suggest future directions and recommendations for developing human-centred systems.

Tweet Classification and Sentiment Analysis of Covid 19 Epidemic by Applying Hybrid Based Techniques

Abstract: World wide spread of COVID-19 pandemic, is throttling the normal life nearly for two years and claiming millions of life all over the globe. Starting from Wuhan of China it crosses more than 200 countries, thereby imposing a overwhelming challenge to health care system. On the other hand, there has been unprecedented advancement of the social media, namely, Twitter, Facebook, WhatsApp and Instagram etc. in an exponential manner. The essence of this paper is to extract and elucidate the opinion or sentiments of the people all around the globe regarding Coronavirus pandemic based on Twitter data. The analysis are based on both lexicon-based approach followed by machine learning algorithms and aims to express the state-of-the-art of the sentiment analysis on the current Coronavirus epidemic prevailing in the entire world and the awareness of the people regarding the disease, its symptoms and impact followed by the preventive measures that need to be undertaken.

New Approach to Sentiment Polarity Detection by using ML Techniques

Abstract: Sentiment analysis (SA) is a process of extracting the user’s feelings, emotions and verifying whether a user-generated text expresses neutral, positive or negative opinion about a product, people, topic or an event. The development of internet based applications has directed enormous measure of customized surveys for different related data on the Web. These reviews can be collected from various sources such as social media, social network, Wiki, forums, blogs, news and websites. As a result of the growing number of customer reviews, finding appropriate customer reviews will play important rule in reducing information overload. Sentiment Analysis is considered as one of the useful tool for users to extract the required data, as well as to aggregate the collective sentiments of the reviews. Because of rapid development of social media and Internet technologies, sentiment analysis has turned into an essential opinion mining technique. There are three noteworthy systems being utilized for sentiment analysis; Machine learning, dictionary based, and rule-based methodology. Each individual method is having some limitations. So in order to overcome these limitations in this paper we proposes an integrated framework which combines the above methods to achieve better scalability and accuracy. Keywords: Sentiment Analysis, Machine Learning, Text Summarization, Review Analysis, Opinion Mining