Sentiment analysis using TF–IDF weighting of UK MPs’ tweets on Brexit

Zhou

et al. 2022

Humanit Soc Sci Commun

Disclosure of patients’ travel route information by government departments has been an effective and indispensable pandemic prevention and control measure during the COVID-19 pandemic. However, this measure may make patients susceptible to cyber violence (CV). We selected 13 real cases that occurred in China during the COVID-19 pandemic for analysis. We identified several characteristics that commonly appeared due to route information, such as rumors about and moral condemnation of patients, and determined that patients who are the first locally confirmed cases of a particular wave of the pandemic are more likely to be the victims of CV. We then analyzed and compared six real cases using data mining and network analysis approaches. We found that disclosing travel route information increases the risk of exposing patients to CV, especially those who violate infection prevention regulations. In terms of disseminating information, we found that mainstream media and influential we-media play an essential role. Based on the findings, we summarized the formation mechanism of route information disclosure-caused CV and proposed three practical suggestions—namely, promote the publicity of the media field with the help of mainstream media and influential we-media, optimize the route information collection and disclosure system, and ease public anxiety about the COVID-19 pandemic. To our knowledge, this study is one of the first to focus on CV on social media during the COVID-19 pandemic. We believe that our findings can help governments better carry out pandemic prevention and control measures on a global scale.

Section: Methodsmentioning

confidence: 99%

Cyber violence caused by the disclosure of route information during the COVID-19 pandemic

Zhou

et al. 2022

Humanit Soc Sci Commun

“…TF-IDF (Term Frequency-Inverse Document Frequency) is one of the popular methods for weighting words. The idea of TF-IDF is that it calculates the frequency of each token in a tweet [19]. Because each tweet is varied in length, a term may occur more frequently in a long tweet than in a short tweet.…”

Section: Feature Extractionmentioning

confidence: 99%

Analysis and Evaluation of Two Feature Selection Algorithms in Improving the Performance of the Sentiment Analysis Model of Arabic Tweets

Yousef¹,

Alali²

2022

IJACSA

Recently, Sentiment analysis from Twitter is one of the most interesting research disciplines; it combined data mining technologies with natural language processing techniques. The sentiment analysis system aims to evaluate the texts that are posted on social platforms to express positive, negative, or neutral feelings of people regarding a certain domain. The high dimensionality of the feature vector is considered to be one of the most popular problems of Arabic sentiment analysis. The main contribution of this paper is to solve the dimensionality problem by presenting a comparative study between two feature selection algorithms, namely, Information Gain (IG), and Chi-Square to choose the best one which may lead to improve the classification accuracy. In this paper, the Arabic Jordanian sentiment analysis model is proposed through four steps. First, a preprocessing step has been applied to the database and includes (Remove Non-Arabic Symbols, Tokenizing, Arabic Stop Word Removal, and Stemming). In the second step, the TF-IDF algorithm is used as a feature extraction method to represent the text into feature vectors. Then, we utilized IG and Chi-Square as feature selection steps to obtain the best subset of features and decrease the total number of features. Finally, different algorithms have been used in the classification step such as (SVM, DT, and KNN) to classify the views people have shared on Twitter, into two classes (positive, and negative). Several experiments were performed on Jordanian dialectical tweets using the AJGT database. The experimental results show the following: 1) The information acquisition algorithm outperformed the Chi-Square Algorithm in the feature selection step, as it was able to reduce the number of features from 1170 to 713 and increase the accuracy of the classifiers by 10%, 2) SVM classifier shows the greatest classification performance among all the classifiers tested which gives the highest accuracy of 85% with IG algorithm.

International Journal of Big Data and Analytics in Healthcare

“…Accordingly, the significance of a word increases as it appears more frequently in the document. However, the importance is balanced by the number of times the word appears in the corpus (Mee et al, 2021). 2.…”

Section: System Modelmentioning

confidence: 99%

“…Furthermore, IDF determines the frequency of the word in the corpus. TF-IDF enables machine learning and deep learning models to obtain the important words (Mee et al, 2021).…”

Section: Feature Extractionmentioning

confidence: 99%

Data Analytics in the Pharmacology Domain

Helae

Alzhouri

2022

Data mining approaches such as natural language processing play a fundamental role in the healthcare sector and, exclusively, the pharmacology domain. The substantial feedback and experiences shared by the patients on different drugs are employed to perform opinion mining on the reviews, which will help the decision-makers to improve the medications' quality and provide the optimal medical outcomes. Based on that, the drug review data set from the UCI machine learning repository is used. The objective of this study is to conduct a sentiment analysis of the patients' reviews to obtain their satisfaction with different drugs using the random forest (RF) machine learning model. In addition, finding out the best drugs for different conditions based on patients' reviews is done by implementing the long short-term memory. Finally, the authors predict the patients' medical conditions based on their reviews by performing the support vector machine and RF classifiers. The knowledge of the patients' medical condition and satisfaction will lead to a noticeable improvement in the pharmaceutical and medical consequences.