Analysis of Social Media Discussions on (#)Diet by Blue, Red, and Swing States in the U.S

Green-Labelled Rice versus Conventional Rice: Perception and Emotion of Chinese Consumers Based on Review Mining

The COVID-19 pandemic increased public health awareness, changing consumers' sensitivity and beliefs about food health. Food anxiety and health scares turn consumers toward safe and healthy foods to strengthen their immunity, which makes green food more popular. However, it remains unclear how to understand the gap between consumer intention to purchase green food and their actual purchasing behaviour. Taking rice as an object of study, comparing differences in consumer perceptions and emotions towards green-labelled rice and conventional rice is beneficial for understanding the components and psychological characteristics of consumer perceptions of green food. Therefore, we used topic modelling and sentiment analysis to explore consumers' focus of attention, attitudinal preferences, and sentiment tendencies based on the review (n = 77,429) from JD.com. The findings revealed that (1) consumers' concerns about green-labelled rice are increasing rapidly, and most have a positive attitude; (2) consumers of green-labelled rice are more concerned about origin, aroma, and taste than conventional rice; (3) consumers of conventional rice are more concerned about the cost-performance ratio, while consumers of green-labelled rice are also price-sensitive; (4) green label mistrust and packaging breakage during logistics are the leading causes of negative emotions among consumers of green-labelled rice. This study provides a comparative analysis of consumer perceptions and emotions between the two types of rice, thus revealing the main influencing factors of the intention-behaviour gap and providing valuable consumer insights for the promotion of green consumption and the sustainable development of the green food industry.

Public Attention and Sentiment toward Intimate Partner Violence Based on Weibo in China: A Text Mining Approach

The mobile internet has resulted in intimate partner violence (IPV) events not being viewed as interpersonal and private issues. Such events become public events in the social network environment. IPV has become a public health issue of widespread concern. It is a challenge to obtain systematic and detailed data using questionnaires and interviews in traditional Chinese culture, because of face-saving and the victim’s shame factors. However, online comments about specific IPV events on social media provide rich data in understanding the public’s attitudes and emotions towards IPV. By applying text mining and sentiment analysis to the field of IPV, this study involved construction of a Chinese IPV sentiment dictionary and a complete research framework. We analyzed the trends of the Chinese public’s emotional evolution concerning IPV events from the perspectives of a time series as well as geographic space and social media. The results show that the anonymity of social networks and the guiding role of opinion leaders result in traditional cultural factors such as face-saving and family shame for IPV events being no longer applicable, leading to the spiral of an anti-silence effect. Meanwhile, in the process of public emotional communication, anger often overwhelms reason, and the spiral of silence remains in effect in social media. In addition, there are offensive words used in the IPV event texts that indicate misogyny in emotional, sexual, economic and psychological abuse. Fortunately, mainstream media, as crucial opinion leaders in the social network, can have a positive role in guiding public opinion, improving people’s ability to judge the validity of network information, and formulating people’s rational behaviour.

COVID-19 Vaccine and Social Media in the U.S.: Exploring Emotions and Discussions on Twitter

The understanding of the public response to COVID-19 vaccines is the key success factor to control the COVID-19 pandemic. To understand the public response, there is a need to explore public opinion. Traditional surveys are expensive and time-consuming, address limited health topics, and obtain small-scale data. Twitter can provide a great opportunity to understand public opinion regarding COVID-19 vaccines. The current study proposes an approach using computational and human coding methods to collect and analyze a large number of tweets to provide a wider perspective on the COVID-19 vaccine. This study identifies the sentiment of tweets using a machine learning rule-based approach, discovers major topics, explores temporal trend and compares topics of negative and non-negative tweets using statistical tests, and discloses top topics of tweets having negative and non-negative sentiment. Our findings show that the negative sentiment regarding the COVID-19 vaccine had a decreasing trend between November 2020 and February 2021. We found Twitter users have discussed a wide range of topics from vaccination sites to the 2020 U.S. election between November 2020 and February 2021. The findings show that there was a significant difference between tweets having negative and non-negative sentiment regarding the weight of most topics. Our results also indicate that the negative and non-negative tweets had different topic priorities and focuses. This research illustrates that Twitter data can be used to explore public opinion regarding the COVID-19 vaccine.

A Systematic Literature Review of Sexual Harassment Studies with Text Mining

Sexual harassment has been the topic of thousands of research articles in the 20th and 21st centuries. Several review papers have been developed to synthesize the literature about sexual harassment. While traditional literature review studies provide valuable insights, these studies have some limitations including analyzing a limited number of papers, being time-consuming and labor-intensive, focusing on a few topics, and lacking temporal trend analysis. To address these limitations, this paper employs both computational and qualitative approaches to identify major research topics, explore temporal trends of sexual harassment topics over the past few decades, and point to future possible directions in sexual harassment studies. We collected 5320 research papers published between 1977 and 2020, identified and analyzed sexual harassment topics, and explored the temporal trend of topics. Our findings indicate that sexual harassment in the workplace was the most popular research theme, and sexual harassment was investigated in a wide range of spaces ranging from school to military settings. Our analysis shows that 62.5% of the topics having a significant trend had an increasing (hot) temporal trend that is expected to be studied more in the coming years. This study offers a bird’s eye view to better understand sexual harassment literature with text mining, qualitative, and temporal trend analysis methods. This research could be beneficial to researchers, educators, publishers, and policymakers by providing a broad overview of the sexual harassment field.

Analysis of Geotagging Behavior: Do Geotagged Users Represent the Twitter Population?

Twitter’s APIs are now the main data source for social media researchers. A large number of studies have utilized Twitter data for diverse research interests. Twitter users can share their precise real-time location, and Twitter APIs can provide this information as longitude and latitude. These geotagged Twitter data can help to study human activities and movements for different applications. Compared to the mostly small-scale data samples in different domains, such as social science, collecting geotagged data offers large samples. There is a fundamental question whether geotagged users can represent non-geotagged users. While some studies have investigated the question from different perspectives, they did not investigate profile information and the contents of tweets of geotagged and non-geotagged users. This empirical study addresses this limitation by applying text mining, statistical analysis, and machine learning techniques on Twitter data comprising more than 88,000 users and over 170 million tweets. Our findings show that there is a significant difference (p-value < 0.001) between geotagged and non-geotagged users based on 73% of the features obtained from the users’ profiles and tweets. The features can also help to distinguish between geotagged and non-geotagged users with around 80% accuracy. This research illustrates that geotagged users do not represent the Twitter population.