Aspect-based Sentiment Analysis using Dependency Parsing

In this paper, an aspect-based Sentiment Analysis (SA) system for Hindi is presented. The proposed system assigns a separate sentiment towards the different aspects of a sentence as well as it evaluates the overall sentiment expressed in a sentence. In this work, Hindi Dependency Parser (HDP) is used to determine the association between an aspect word and a sentiment word (using Hindi SentiWordNet) and works on the idea that closely connected words come together to express a sentiment about a certain aspect. By generating a dependency graph, the system assigns the sentiment to an aspect having a minimum distance between them and computes the overall polarity of the sentence. The system achieves an accuracy of 83.2% on a corpus of movie reviews and its results are compared with baselines as well as existing works on SA. From the results, it has been observed that the proposed system has the potential to be used in emerging applications like SA of product reviews, social media analysis, etc.

#yeeyeenation

Using methods from country music studies, performance studies, hashtag ethnography, and Black Feminist Thought (BFT), this article employs sonic, discursive, and social media analysis to examine performances of White masculinity known as “country boys.” In the opening sections, I describe examples of country boys that emerge from Texas A&M University (College Station), bringing together confederate statues and the men who identify with and defend such statues. I then turn my focus to critical analysis of one country boy in particular: county music singer, brand progenitor, and Texas icon, Granger Smith a.k.a. Earl Dibbles Jr. Highlighting the importance of country boys to the cultural identity of Texas A&M University, I argue that White publics aggregate and accrue racialized and gendered meaning in social media spaces through signs associated with Smith like the hashtag #yeeyeenation. Such signs are predicated on and normalize a rhetoric—in this case, that something or someone “is not racist”—even in the face of evidence to the contrary. Extending the insights of scholarship on the former Confederacy to contemporary country music cultures and to the present political moment, this article interrogates how White identities and related genealogies in the U.S. context are not simply established to sanitize and excuse expressions of racist, gendered, and exclusionary thought, but are sustained by aestheticized deceptions. I refer to these deceptions as mythopoetics. In this article I demonstrate how Smith’s success, particularly since he is best known for his “redneck” alter-ego, Earl Dibbles Jr., is a testament to the power and reach of mythopoetics in a hegemonic White and heteropatriarchal society. I argue that mythopoetics are not only essential to majoritarian cultural formations today, but also normalize White supremacy to such a point that its violence can circulate without consequence and in plain sight.

HPV Vaccination: Polish-Language Facebook Discourse Analysis

Social media platforms are widely used for spreading vaccine-related information. The objectives of this paper are to characterize Polish-language human papillomavirus (HPV) vaccination discourse on Facebook and to trace the possible influence of the COVID-19 pandemic on changes in the HPV vaccination debate. A quantitative and qualitative analysis was carried out based on data collected with a tool for internet monitoring and social media analysis. We found that the discourse about HPV vaccination bearing negative sentiment is centralized. There are leaders whose posts generate the bulk of anti-vaccine traffic and who possess relatively greater capability to influence recipients’ opinions. At the beginning of the COVID-19 pandemic vaccination debate intensified, but there is no unequivocal evidence to suggest that interest in the HPV vaccination topic changed.

Sentiment Analysis of Social Survey Data for Local City Councils

Big data analytics can be used by smart cities to improve their citizens’ liveability, health, and wellbeing. Social surveys and also social media can be employed to engage with their communities, and these can require sophisticated analysis techniques. This research was focused on carrying out a sentiment analysis from social surveys. Data analysis techniques using RStudio and Python were applied to several open-source datasets, which included the 2018 Social Indicators Survey dataset published by the City of Melbourne (CoM) and the Casey Next short survey 2016 dataset published by the City of Casey (CoC). The qualitative nature of the CoC dataset responses could produce rich insights using sentiment analysis, unlike the quantitative CoM dataset. RStudio analysis created word cloud visualizations and bar charts for sentiment values. These were then used to inform social media analysis via the Twitter application programming interface. The R codes were all integrated within a Shiny application to create a set of user-friendly interactive web apps that generate sentiment analysis both from the historic survey data and more immediately from the Twitter feeds. The web apps were embedded within a website that provides a customisable solution to estimate sentiment for key issues. Global sentiment was also compared between the social media approach and the 2016 survey dataset analysis and showed some correlation, although there are caveats on the use of social media for sentiment analysis. Further refinement of the methodology is required to improve the social media app and to calibrate it against analysis of recent survey data.

Saying Her Name: Gendered Narratives in News Coverage of Breonna Taylor's Death

In 2020, Breonna Taylor was killed in her apartment as police officers served a no-knock warrant. Unlike most cases of police violence against a woman of color, Taylor’s death was eventually deemed newsworthy. Given that people’s perceptions of justice-related issues are often informed by media representations, the way the her death was covered can send critical messages about police violence against women of color. This research note presents the findings of a qualitative media analysis of newspaper coverage of Taylor’s case for the six months following her death. Drawing from research on media depictions of police use of force and women as victims, it explored how gender shaped the media coverage of her case. Findings indicate that while there are similarities to other news coverage of deadly use of force incidents that gender and its intersection with race shaped the narratives in three main ways—by characterizing Taylor through a patriarchal lens suggesting that she is an ideal victim; by shifting blame onto Taylor by focusing on relationships with men; and by addressing media coverage while reporting on her death.

Safe Medicine Administration Counseling for Pregnant and Breastfeeding Mothers

The use of drugs for pregnancy and breastfeeding needs to be self-medication and the importance of counselling to increase the mother's knowledge about the correct use of drugs so that pregnant and lactating women's level of health and knowledge increases. The counselling purpose was to determine the mother's level of knowledge and whether there was a difference in the knowledge level of the use of drugs during pregnancy and lactation. The method used is pre and post-media analysis (flipchart). Data analysis obtain by scoring questionnaires, univariate analysis, and statistical analysis. Mann-Whitney test results showed that in the post-test or after giving counselling using flipchart media, there was a change in respondents' knowledge from before being given a flipchart and after being given a flipchart. The hypothesis from this counselling is accepted, which means that giving flipcharts affects the level of knowledge. The calculations using the spearman test obtained p-value pretest 0.732 and p-value post-test 0.253 for pregnant women and obtained p-value pretest and post-test of 0.033 (p <0.05) for breastfeeding mothers, then there is a relationship between the education level pregnant and lactating mothers with knowledge. The Wilcoxon test data pretest and post-test knowledge of pregnant and lactating mothers had a p-value of 0.003 (p 0.05), the effect of counselling concluded with flipchart media on the knowledge of pregnant and lactating mothers about the use of drugs.

Media Literacy Facilitation as Service Learning and Public Engagement

This chapter offers insights from a 15-year partnership between a public university and local K-12 schools to explore how the facilitation of media literacy education (MLE) programs by university students can offer rewarding outcomes for both research and learning. The MLE program that serves as the case study for this chapter takes place at local elementary schools each spring in conjunction with an undergraduate communication course and includes interactive media analysis discussions as well as a culminating creative production activity. Reflections and written feedback from participating graduate, undergraduate, and elementary students emphasize the strengths of this pedagogical model for collaboration and learning while also acknowledging the practical constraints of such a partnership. By detailing the institutional-level support, instructional design, and practical implementation of this MLE program, the chapter enumerates the benefits and challenges of engaged research and service learning for advancing media literacy goals.

Sadness, Negativity, and Uncertainty in Education During COVID-19 on Social Media

The global COVID-19 pandemic increased social media usage to obtain information and to share concerns, feelings, and emotions, turning it into a prolific field of research through which it is possible to understand how audiences are coping with the multitude of recent challenges. This paper presents results from a social media analysis of 61532 education-related news headlines posted by the major daily news provider in Portugal, Sic Notícias, on Facebook, from January to December 2020. We focus on how the news impacted on audiences’ emotional response and discourse, and we analyze the key issues of the most commented news content. The results show a prevailing sadness among audiences and a very negative discourse all throughout 2020, with a high degree uncertainty being expressed. The main concerns revolved around parents supporting children in their first remote learning endeavors, financial sustainability, the lack of devices, the disinfection of schools, and the students’ mobility, particularly in the non-higher education context.