Number Of Negative Tweets Research Articles

Predicting COVID-19 vaccinators based on machine learning and sentiment analysis

In the past two years, the world witnessed the spread of the coronavirus (COVID-19) pandemic that disrupted the entire world, the only solution to this epidemic was health isolation, and with it everything stopped. When announcing the availability of a vaccine, the world was divided over the effectiveness and harms of this vaccine. This article provides an analysis of vaccinators and analysis of people's opinions of the vaccine's efficacy and whether negative or positive. Then a model is built to predict the future numbers of vaccinators and a model that predicts the number of negative opinions or tweets. The model consists of three stages: first, converting data sets into a synchronized time series, that is, the same place and time for vaccination and tweets. The second stage is building a prediction model and the third stage was descripting analysis of the prediction results. The autoregressive integrated moving averages (ARIMA) method was used after decomposing the components of ARIMA and choosing the optimal model, the best results obtained from seasonal ARIMA (SARIMA) for both predictions, the last stage is the descriptive analysis of the results and linking them together to obtain an analysis describing the change in the number of vaccinators and the number of negative tweets.

Sentiment analysis on Education transformation during Covid-19 using Arabic tweets in KSA.

The emergence of COVID-19 pandemic has changed the whole world. To prevent the spread of the virus, different precautionary measure and policies have been defined, one of them is distance learning. It has led to the educational transformation from physical education to online learning. Similarly, in KSA online education is adopted since March 2020. Inorder to extract the individual perception about the online education in KSA, twitter data was used. Arabic tweets were collected using twitter API. Furthermore, several machine learning models such as Support Vector Machine (SVM), Naïve Bayes (NB), Random Forest (RF), Logistic regression, K-nearest neighbors was used develop an automated sentiment analysis of online education related tweets in KSA. For feature extraction and selection N-gram and Term Frequency–Inverse Document Frequency (TF-IDF) was used. Logistic Regression achieved the highest accuracy of 69.33% for multiclass and Random Forest achieved accuracy of 80.35%. According to the dataset, most of the individuals have negative opinion about the online learning as the number of negative tweets are higher as compared to positive and neutral class

Support Vector Machine for Sentiment Analysis of Nigerian Banks Financial Tweets

The rise of social media paves way for unprecedented benefits or risks to several organisations depending on how they adapt to its changes. This rise comes with a great challenge of gaining insights from these big data for effective and efficient decision making that can improve quality, profitability, productivity, competitiveness and customer satisfaction. Sentiment analysis is the field that is concerned with the classification and analysis of user generated text under defined polarities. Despite the upsurge of research in sentiment analysis in recent years, there is a dearth in literature on sentiment analysis applied to banks social media data and mostly on African datasets. Against this background, this study applied machine learning technique (support vector machine) for sentiment analysis of Nigerian banks twitter data within a 2-year period, from 1st January 2017 to 31st December 2018. After crawling and preprocessing of the data, LibSVM algorithm in WEKA was used to build the sentiment classification model based on the training data. The performance of this model was evaluated on a pre-labelled test dataset generated from the five banks. The results show that the accuracy of the classifier was 71.8367%. The precision for both the positive and negative classes was above 0.7, the recall for the negative class was 0.696 and that of the positive class was 0.741 which shows the prediction did better than chance in addition to other measures. Applying the model in predicting the sentiments of the five Nigerian banks twitter data reveals that the number of positive tweets within this period was slightly greater than the number of negative tweets. The scatter plots for the sentiments series indicated that, majority of the data falls between 0 and 100 sentiments per day, with few outliers above this range.

Evaluatieve tweets van studenten en het effect van een interventie door docent-volgers

In this study, 21,085 tweets from university students over a period of twelve weeks were analyzed. Our aim was to investigate the number and evaluative content of students’ tweets related to their study, and to know whether the number of negative tweets decreases when teachers follow students on Twitter. About thirteen percent of all students’ tweets relate to their study. We categorized these in student-centered (10%) or curriculum-centered (3%), and divided both categories in negative (4%) or positive (9%) tweets. Teachers became followers of their students after six weeks, which led to a significant decrease of negative curriculum-centered tweets (from 2.2 to 0.7%), although a small decrease was observed even before the intervention started. Contrary to the teachers’ initial fears, it is unlikely that students ‘infect’ each other with negative evaluations about the curriculum, since the number of negative tweets is very low overall.