A study on the sentiments and psychology of twitter users during COVID-19 lockdown period

Public Opinion About COVID-19 on a Microblog Platform in China: Topic Modeling and Multidimensional Sentiment Analysis of Social Media

BACKGROUND

The COVID-19 pandemic raised wide concern from all walks of life globally. Social media platforms became an important channel for information dissemination and an effective medium for public sentiment transmission during the COVID-19 pandemic.

OBJECTIVE

Mining and analyzing social media text information can not only reflect the changes in public sentiment characteristics during the COVID-19 pandemic but also help the government understand the trends in public opinion and reasonably control public opinion.

METHODS

First, this study collected microblog comments related to the COVID-19 pandemic as a data set. Second, sentiment analysis was carried out based on the topic modeling method combining latent Dirichlet allocation (LDA) and Bidirectional Encoder Representations from Transformers (BERT). Finally, a machine learning linear regression (ML-LR) model combined with a sparse matrix was proposed to explore the evolutionary trend in public opinion on social media and verify the high accuracy of the model.

RESULTS

The experimental results show that, in different stages, the characteristics of public emotion are different, and the overall trend is from negative to positive.

CONCLUSIONS

The proposed method can effectively reflect the characteristics of the different times and space of public opinion. The results provide theoretical support and practical reference in response to public health and safety events.

Volatility of the COVID-19 vaccine hesitancy: sentiment analysis conducted in Brazil

Background

Vaccine hesitancy is a phenomenon that can interfere with the expansion of vaccination coverage and is positioned as one of the top 10 global health threats. Previous studies have explored factors that affect vaccine hesitancy, how it behaves in different locations, and the profile of individuals in which it is most present. However, few studies have analyzed the volatility of vaccine hesitancy.

Objective

Identify the volatility of vaccine hesitancy manifested in social media.

Methods

Twitter's academic application programming interface was used to retrieve all tweets in Brazilian Portuguese mentioning the COVID-19 vaccine in 3 months (October 2020, June 2021, and October 2021), retrieving 1,048,576 tweets. A sentiment analysis was performed using the Orange software with the lexicon Multilingual sentiment in Portuguese.

Results

The feelings associated with vaccine hesitancy were volatile within 1 month, as well as throughout the vaccination process, being positioned as a resilient phenomenon. The themes that nurture vaccine hesitancy change dynamically and swiftly and are often associated with other topics that are also affecting society.

Conclusion

People that manifest the vaccine hesitancy present arguments that vary in a short period of time, what demand that government strategies to mitigate vaccine hesitancy effects be agile and counteract the expressed fear, by presenting scientific arguments.

Deterministic solution of algebraic equations in sentiment analysis

Text mining methods usually use statistical information to solve text and language-independent procedures. Text mining methods such as polarity detection based on stochastic patterns and rules need many samples to train. On the other hand, deterministic and non-probabilistic methods are easy to solve and faster than other methods but are not efficient in NLP data. In this article, a fast and efficient deterministic method for solving the problems is proposed. In the proposed method firstly we transform text and labels into a set of equations. In the second step, a mathematical solution of ill-posed equations known as Tikhonov regularization was used as a deterministic and non-probabilistic way including additional assumptions, such as smoothness of solution to assign a weight that can reflect the semantic information of each sentimental word. We confirmed the efficiency of the proposed method in the SemEval-2013 competition, ESWC Database and Taboada database as three different cases. We observed improvement of our method over negative polarity due to our proposed mathematical step. Moreover, we demonstrated the effectiveness of our proposed method over the most common and traditional machine learning, stochastic and fuzzy methods.

An analysis of patient motivation for seeking online treatment for binge eating disorder-A mixed methods study combining systematic text condensation with sentiment analysis

OBJECTIVE

Online treatment for binge eating disorder (BED) is an easily available option for treatment compared to most standard treatment procedures. However, little is known about how motivation types characterize this population and how these impact treatment adherence and effect in an online setting. Therefore, we aimed to investigate a sample of written motivation statements from BED patients, to learn more about how treatment and online treatment in particular, presents in this population.

METHODS

Using self-determination theory in a mixed methods context, we investigated which types of motivation were prevalent in our sample, how this was connected with patient sentiment, and how these constructs influence treatment and adherence.

RESULTS

Contrary to what most current literature suggests, we found that in our sample (n = 148), motivation type was not connected with treatment outcome. We did find a strong association between sentiment scores and motivation types, indicating the model is apt at detecting effects. We found that when comparing an adult and young adult population, they did not differ in motivation type and the treatment was equally effective in young adults and adults. In the sentiment scores there was a difference between sentiment score and adherence in the young adult group, as the more positive the young adults were, the less likely they were to complete the program.

DISCUSSION

Because motivation type does not influence online treatment to the same degree as it would in face-to-face treatment it indicates that the typical barriers to treatment may be less crucial in an online setting. This should be considered during intake; as less motivated patients may be able to adhere better to online treatment, because the latter imposes fewer barriers of the kind that only strong motivation can overcome. The fact that motivation type and sentiment score of the written texts are strongly associated, indicate a potential for automated models to detect motivation based on sentiment.

How Does the World View China’s Carbon Policy? A Sentiment Analysis on Twitter Data

China has recently put forth an ambitious plan to achieve carbon peak around 2030 and carbon neutrality around 2060. However, there are quite a few differences regarding the public views about China’s carbon policy between the Chinese people and the people from other countries, especially concerning the doubt of foreign people about the fidelity of China’s carbon policy goals. Based on Twitter data related to China’s carbon policy topics from 2008 to 2020, this study shows the inter- and intra-annual trends in the count of tweets about China’s carbon policy, conducts sentiment analysis, extracts top frequency words from different attitudes, and analyzes the impact of China’s official Twitter accounts on the global view of China’s carbon policy. Our results show: (1) the global attention to China’s carbon policy gradually rises and occasionally rises suddenly due to important carbon events; (2) the proportion of Twitter users with negative sentiment about China’s carbon policy has increased rapidly and has exceeded the proportion of Twitter users with positive sentiment since 2019; (3) people in developing countries hold more positive or neutral attitudes towards China’s carbon policy, while developed countries hold more negative attitudes; (4) China’s official Twitter accounts serve to improve the global views on China’s carbon policy.