YouTube Comments Research Articles

Deliberation in online political talk: exploring interactivity, diversity, rationality, and incivility in the public spheres surrounding news vs. satire

Abstract Political satire is often believed to enrich the public sphere in ways distinct from traditional journalism. This study examines whether deliberative qualities of online political talk in response to satire differ from those in response to regular news or partisan news. The analysis focuses on four normative standards: interactivity, diversity, rationality, and civility. A manual content analysis of YouTube comments (n = 2,447) reveals that the public sphere surrounding political satire shows a notable strength: Less incivility, both in terms of impoliteness and intolerance. Surprisingly, aside from this, satire’s public sphere did not differ much from that of regular news. Comments on partisan news were more opinionated and ideologically diverse. These findings suggest that online political talk prompted by satire is not inferior to that of traditional news. Additionally, this study highlights how the presence of different normative standards is often interconnected.

Avatars at Risk: Exploring Public Response to Sexual Violence in Immersive Digital Spaces

As the metaverse emerges as a new frontier of human interaction, understanding public perceptions of crime in virtual spaces becomes crucial. This study delves into public perceptions of such crimes, focusing on reported incidents of sexual assault in virtual reality environments. We uncover complex dynamics, shaping threat perception in immersive digital realms by analysing YouTube comments through an innovative mixed-methods approach combining machine learning and empirical analysis. Our findings reveal that social norms and expectations are pivotal in influencing perceptions of threats, while technology-mediated interactions correlate with reduced perceived risks. Surprisingly, the oft-discussed blurring of virtual and physical realities shows no significant impact on threat perception. This research contributes to the expanding literature on the social construction of reality and public perception of emerging technologies. The results have implications for the development and governance of metaverse platforms, highlighting the necessity for comprehensive user education initiatives and culturally sensitive approaches to community guidelines and safety features.

Analyzing Public Discourse on the Affordable Care Act through YouTube Comments

Abstract Introduction Social media’s pervasive role in daily life provides a unique avenue for understanding public sentiments. This study utilizes YouTube comments on an MSNBC video about the Affordable Care Act (ACA) to explore public opinions on the policy and its political implications. Methods A qualitative analysis of YouTube comments on an MSNBC video was conducted. Netlytic, a scraping tool, gathered 1,949 comments. Thematic analysis, based on a coding framework derived from Semetko and Valkenburg’s frames, identified three predominant frames: Responsibility, Human Interest, and Economic Consequences. Results Of the 1949 comments posted in response to the ACA video on YouTube, 488 were analyzed. Three media frames were used to categorize the comments. Among the analyzed comments, 42% fell within the Responsibility Frame, indicating that 205 comments attributed responsibility for ACA-related issues, healthcare access, and costs to political parties, individual politicians, and government entities. The Human-Interest Frame accounted for 11% of the comments, with 53 remarks reflecting individual experiences related to healthcare access and costs. Additionally, 26% of the comments fell within the Economic Consequences Frame, signifying those 125 comments included remarks concerning the economic impacts of the ACA, such as increased healthcare access, taxes, and penalties. The remaining 21% of comments did not align with the three frames. Conclusions This study embarked on a comprehensive exploration of public discourse surrounding the Affordable Care Act (ACA) within the context of the 2024 presidential election, utilizing YouTube comments as a rich source of qualitative data. Through a meticulous methodological approach, which included thematic framing analysis and intercoder reliability assessments, valuable insights into the diverse perspectives and sentiments expressed by social media users regarding this critical healthcare legislation were gained. Key messages • Social media allows for real-time understanding of people’s thoughts, beliefs, opinions, and ideas, as well as serves as a useful tool that fosters broad, unfiltered data/content. • Researchers conducted a qualitative analysis of public discourse on YouTube to explore the range of sentiments regarding the ACA.

The ninth art, tells the story of cultural China and the world: Cultural interaction in cross-cultural video game communication-based on 'Genshin Impact' YouTube comments.

China has attached increasing importance to the overseas dissemination of traditional culture as it continues to strengthen its comprehensive national strength and develop globalization initiatives. The electronic game, as the 'ninth art', with its booming development and inherent cross-cultural communication platform attributes, has taken on the important task of taking culture abroad. This study selects 'Genshin Impact', a game highly praised and well-received globally, which contains an abundance of Chinese cultural elements and cultural elements from various regions of the world, to study cultural interaction in cross-cultural communication of electronic games. This study conducts text sentiment analysis and semantic network analysis on the comments of 'Genshin Impact' videos on the overseas video platform YouTube and studies the cultural interaction in the cross-cultural communication of the 'ninth art', telling the cultural stories of China and the world from a multicultural perspective. The study found that games and derivative videos triggered positive emotional responses from audiences both at home and abroad. While experiencing pleasure and surprise, audiences also arouse deeper emotions such as admiration, identification, and expectation. Meanwhile, in the complex art form of the 'ninth art', audiences can absorb the cultural elements of different cultures, resonate with the elements of their cultural circle, and even trigger further profound thinking. Finally, this study provides constructive suggestions on using the 'ninth art' to better 'tell China's stories and disseminate China's voice'.

Sentiment Analysis of Political Parties on social media: A Machine Learning and Lexicon-Based Approach

Social media platforms like Facebook, Twitter, Instagram, and YouTube have become central to communication and entertainment, with users sharing opinions on various topics. These opinions, often categorized as positive, negative, or neutral sentiments, provide valuable data for sentiment analysis. Our research analyzed political YouTube comments related to India’s Bhartiya Janata Party (BJP) and Indian National Congress (INC) using a combination of the AFINN lexicon and machine learning techniques. We applied feature representation methods such as Bag of Words (BoW) and Term Frequency-Inverse Document Frequency (TF-IDF), alongside five machine learning algorithms: Multinomial Naïve Bayes, Logistic Regression, Random Forest, Support Vector Machine (SVM), and K-nearest neighbor (K-NN). We aimed to determine the most efficient sentiment analysis approach by comparing the performance of these models using standard evaluation metrics. For the BJP dataset, Logistic Regression performed best with BoW, while SVM was most effective with TF-IDF. Similarly, for the INC dataset, Random Forest excelled with BoW, and SVM outperformed others with TF-IDF. The AFINN lexicon showed poor performance across both datasets, and K-NN consistently achieved lower accuracy. Our findings suggest that SVM and Random Forest are more suitable for political sentiment analysis.

Biased Social Media Debates About Terrorism? A Content Analysis of Journalistic Coverage of and Audience Reactions to Terrorist Attacks on YouTube

Social media are an important source of news during crises such as terrorist attacks. However, how news media and their audiences make sense of terrorism on social media is subject to bias, for example, given their differential treatment of terrorism by right-wing versus Islamist extremist perpetrators. In this study, we analyze how incident- and perpetrator-related characteristics of terrorist attacks are associated with bias in public debates about terrorism on YouTube. We focus on selectiveness in which attacks are covered (gatekeeping bias), how attacks are covered (presentation bias), and how audiences react to coverage (audience bias). Methodologically, we employ a manual and an automated content analysis of terrorism coverage by five international broadcasters on YouTube ( N = 643, 2018–2020) and related user comments ( N = 193,721). Our findings illustrate how sociocultural contexts shape news bias in terrorism coverage, both in the form of gatekeeping bias and presentation bias—but we conclude with less evidence for audience bias in public reactions to terrorism, at least on social media. Consequently, journalists should critically question working routines in covering crises to avoid reinforcing power imbalances, especially those from Western contexts.

Text Analytics on YouTube Comments for Food Products

YouTube is a popular social media platform in the contemporary digital landscape. The primary focus of this study is to explore the underlying sentiment in user comments about food-related videos on YouTube, specifically within two pivotal food categories: plant-based and hedonic product. We labeled comments using sentiment lexicons such as TextBlob, VADER, and Google’s Sentiment Analysis (GSA) engine. Comment sentiment was classified using advanced Machine-Learning (ML) algorithms, namely Support Vector Machines (SVM), Multinomial Naive Bayes, Random Forest, Logistic Regression, and XGBoost. The evaluation of these models encompassed key macro average metrics, including accuracy, precision, recall, and F1 score. The results from GSA showed a high accuracy level, with SVM achieving 93% accuracy in the plant-based dataset and 96% in the hedonic dataset. In addition to sentiment analysis, we delved into user interactions within the two datasets, measuring crucial metrics, such as views, likes, comments, and engagement rate. The findings illuminate significantly higher levels of views, likes, and comments in the hedonic food dataset, but the plant-based dataset maintains a superior overall engagement rate.

Frame exploitation at its worst

Abstract Although essential to science and health communication, metaphors can backfire. At this point, any attempt on the part of the speaker to clarify his/her intentions would ultimately prove futile because the mental situation models of speakers and their recipients may not be the same. A debate over the meaning of a metaphor, the variations in its interpretation, or constant negotiation between the interactants poses a substantial challenge to intention-based theories of implicature. A corpus analysis of the “kofta” analogy used by a senior Egyptian army doctor during a February 2014 televised news conference to announce cures for AIDS and hepatitis C and the ensuing impasse over its appropriateness shows that a metaphor designed to publicly communicate science, to confront and shatter the stereotypical image of scientists as dull and stilted people, to persuade citizens to accept the claims as fact, or to hide the speaker’s own scientific ignorance may be sarcastically repeated, extended, and elaborated (“overexploited”) by the target audience (“overdone metaphors”). The doctor or his use of the metaphor of “I give [the virus] back as a kebab skewer for the patient to feed on” has been condemned as “too lower class”. Various forms of metaphor denial and resistance are examined. The article, analyzing thousands of YouTube comments on the news conference video, provides valuable insights for interpreting tropes and has important implications both for science and health communicators and socio-cognitive pragmaticists.

Public sentiment on the Israeli–Palestinian conflict: insights from YouTube, Mastodon, and Google Trends

ABSTRACT This research employs a comprehensive methodology to delve into public sentiments surrounding the Israeli–Palestinian conflict, incorporating unconventional data sources—YouTube comments and Mastodon. Departing from the traditional reliance on Twitter, our systematic approach involves keyword-driven content identification, leveraging Google Trends to establish five pivotal keywords. Mastodon searches employed straightforward hashtag strategies, while the intricacies of YouTube required an exclusive focus on official newspaper channels to mitigate polarization risks. Rigorous data cleaning ensued, retaining only English-language texts and eliminating extraneous elements. The resulting dataset was subjected to Sentiment Analysis and Emotion Detection, providing a nuanced understanding of public sentiments across platforms, totaling 253.3 K texts.

Harvesting Insights: Sentiment Analysis on Smart Farming YouTube Comments for User Engagement and Agricultural Innovation

Harvesting Insights: Sentiment Analysis on Smart Farming YouTube Comments for User Engagement and Agricultural Innovation

Enhancing the design of voting advice applications with BERT language model.

The relevance and importance of voting advice applications (VAAs) are demonstrated by their popularity among potential voters. On average, around 30% of voters take into account the recommendations of these applications during elections. The comparison between potential voters' and parties' positions is made on the basis of VAA policy statements on which users are asked to express opinions. VAA designers devote substantial time and effort to analyzing domestic and international politics to formulate policy statements and select those to be included in the application. This procedure involves manually reading and evaluating a large volume of publicly available data, primarily party manifestos. A problematic part of the work is the limited time frame. This study proposes a system to assist VAA designers in formulating, revising, and selecting policy statements. Using pre-trained language models and machine learning methods to process politics-related textual data, the system produces a set of suggestions corresponding to relevant VAA statements. Experiments were conducted using party manifestos and YouTube comments from Japan, combined with VAA policy statements from six Japanese and two European VAAs. The technical approaches used in the system are based on the BERT language model, which is known for its capability to capture the context of words in the documents. Although the output of the system does not completely eliminate the need for manual human assessment, it provides valuable suggestions for updating VAA policy statements on an objective, i.e., bias-free, basis.

SENTIMENT ANALYSIS OF YOUTUBE COMMENTS ON WISH 107.5 VIDEOS USING NATURAL LANGUAGE PROCESSING (NLP)

Wish 107.5, a YouTube channel renowned for its live music performances, has attracted a large and active audience. Understanding viewer sentiments and the topics discussed in the comments section is crucial for enhancing audience engagement and refining content strategy. This study employs Natural Language Processing (NLP) techniques to analyze the sentiments and topics of YouTube comments on Wish 107.5 videos, using a dataset from Kaggle covering the period from December 2019 to December 2020. Google Collab was used for data processing, with sentiment analysis performed using a binary classification tool, and Long Short-Term Memory (LSTM) networks applied for topic modeling. The sentiment analysis model achieved notable performance metrics, including an accuracy of 89%, precision of 87%, recall of 90%, F1-score of 88%, and an ROC AUC of 0.92, demonstrating its effectiveness in classifying YouTube comments. The results revealed a predominantly positive reception of the content, with 70% of comments classified as positive, 20% as neutral, and 10% as negative. Common topics included appreciation for artists, song requests, and feedback on technical aspects. While the model exhibited a training accuracy nearing 1.0, the validation accuracy was 0.78, indicating some overfitting. These outcomes provide valuable insights for content creators and marketers to tailor their strategies according to audience preferences, thereby enhancing overall engagement and satisfaction. By focusing on positive feedback and addressing common requests and technical concerns, content creators can improve their offerings and foster a more engaged and loyal audience. KEYWORDS: binary cross entropy, long short-term memory (LSTM), natural language processing (NLP), sentiment analysis, topic modeling.

Mediated public perceptions of police encampment clearances in Canada and France: a cross-national study

ABSTRACT This qualitative study investigates public perceptions of police encampment clearances in Canada and France. Our focus is on how YouTube users in these two countries judge police conduct in response to videos of police clearing encampments. Research on police public perceptions and police legitimacy typically focuses on public views of the police institution and perceptions stemming from direct interactions with officers. An analysis of YouTube comments on police intervention videos offers important insights into a relatively unexplored intermediate case: the mediated judgements on concrete, specific police action from individuals outside of the perceived police intervention. Further, the scholarship specifically examining social media and public perceptions of policing in cross-national contexts is almost nonexistent. To address these gaps, we ask the following: What do comments on YouTube in response to videos of police encampment clearances reveal about police legitimacy in Canada and France as perceived by social media users? A total of 8,091 user-generated comments across 25 Canadian YouTube videos and 7,086 comments across 29 French YouTube videos were collected, sorted, and examined using qualitative media analysis. Our analysis confirms that the issue of police legitimacy generates dissensus and polarisation. It demonstrates that public perceptions of the legitimacy of the police clearance are strongly tied to the legitimacy of the encampment itself, and more broadly to moral judgements about the groups targeted by the police. Our findings also reveal that French police are more often perceived as violent than their Canadian counterparts.

What sources do individuals use to validate arguments in scientific discourses today? An exploratory study of YouTube comments on vaccination

PurposeThis study aims to explore scientific discourses on vaccination in YouTube comments using the Connectivism theory as a foundational guide in the inquiry of understanding knowledge seeking and sharing. The authors sought to understand how individuals share and seek information by using external sources through URL links to validate their arguments.Design/methodology/approachUsing content analysis, the authors extracted and analysed 584 random comments with URL links from eight YouTube videos scientifically addressing the purpose of vaccines. The comments were coded by stance (pro, anti, and neutral) and the type of resource to observe how their links were used.FindingsThe results showed that URL links were composed of quotes, questions, and opinions. Many sources came from research papers, conspiracy websites, or other videos. Some of the comments did not accurately reflect the information from research papers and showed little scientific reasoning. This suggests the need for critical evaluation among individuals when finding information online.Research limitations/implicationsThe findings can be expanded to explore different types of information literacy practices in the comment section of social media for both informal and formal environments.Practical implicationsYouTube is useful in fostering scientific discourse and information-seeking/sharing practices among individuals. However, considering the inaccuracy of content deliverance, educators and individuals will need to consider how to teach/conduct information literacy skills when implementing social media for educational purposes.Originality/valueOnly a few studies have conducted research on comments using URL links, the originality of sources and how the sources were used in argumentation.

Sentiment Analysis of YouTube Comments on the Movie 'Zindagi Tamasha': Evaluating Public Perception and Social Impact Post-Ban

Sentiment Analysis of YouTube Comments on the Movie 'Zindagi Tamasha': Evaluating Public Perception and Social Impact Post-Ban

Examining Indonesia’s Aggression towards Malaysia over Tari Pendet Dispute in Youtube Comments: The Role of Collective Narcissism

This study analyses themes that emerged in discussions on YouTube comments by Indonesian regarding the 2009 Pendet Dance controversy. The research uses netnography methods with a qualitative approach. Using Netlytic, corpus was collected from YouTube under 'Malaysian Pendet Dance' keyword. There are 1030 comments gathered from 4 relevant videos. The corpus was selected and eliminated to 52 comments. For comparison, the corpus is divided based on the upload period, marked by the time Discovery Channel apologized to Indonesia. Based on collective narcissism understanding, researcher frames the emerging themes and sub-themes related to the nature of collective narcissism. The themes and sub-themes of the comments were then coded, compared, and projected with the help of NVivo software. The results show that there is a development of stacking narcissism themes across periods. The collective narcissism themes found in the 2009 period were aggressiveness; desire for justification and other nations’ recognition of own culture; prejudice which causes hostility. Meanwhile, during the commentary period from 2010 to present, the same themes are found, with the addition of sub-themes and three new main themes namely the hardship of forgetting old wounds; see oneself as a tortured victim; and radicalism-to which brought another issue. The conflict between the Indonesian and Malaysian began in 1963 in the Borneo conflict and still ongoing. The collective narcissism that Indonesian society displays towards Malaysia is mediated by the ideology of blind patriotism and the perceived threat to the group by external aggression.

CHILDFREE DAN RUANG PUBLIK: RESEPSI WARGANET TERHADAP PEREMPUAN CHILDFREE DALAM KOLOM KOMENTAR PADA KANAL YOUTUBE METRO TV NEWS

This study is motivated by the childfree choice for women which is now starting to become a new lifestyle among young Indonesian couples. This phenomenon is of course inversely proportional to the normative culture of Indonesian society, which expects married adults to have children. The childfree phenomenon then became a topic of conversation among netizens, especially in the YouTube comments space. This research aims to analyze and understand netizens' reception of childfree women in the video comment space entitled "Kick Andy- Childfree". Apart from that, to strengthen the role of the audience not only as consumers of media but also as producers of meaning. This research is located on the Metrotvnews Youtube channel which was uploaded on April 25 2022. Data sources are videos and comment transcripts which are analyzed using reception analysis. This research produced several findings that can be studied including; 1) Childfree choices and 'selfish choices' 2) Having children and social expectations 3) Childfree choices to 'enjoy the fruits of one's labor' 4) Women and a mother's 'natural instincts'. The findings show that there is a variety of acceptance of childfree women, ranging from comments that approve, praise, to reject. A message can be interpreted differently by netizens based on different sociocultural backgrounds, personal experiences, knowledge, religion and ethnicity. Even when decoders emphasize certain parts, they still make different readings. The presence of the YouTube comments space as a digital public space (public sphere) shows an increase in users' ability not only to express opinions, but to discuss and spark debate between users on controversial issues.

Misogynistic attitude detection in YouTube comments and replies: A high-quality dataset and algorithmic models

Social media platforms are now not only a medium for expressing users views, feelings, emotions and sentiments but are also being abused by people to propagate unpleasant and hateful content. Consequently, research efforts have been made to develop techniques and models for automatically detecting and identifying hateful, abusive, vulgar, and offensive content on different platforms. Although significant progress has been made on the task, the research on design of methods to detect misogynistic attitude of people in non-English and code-mixed languages is not very well-developed. Non-availability of suitable datasets and resources is one main reason for this. Therefore, this paper attempts to bridge this research gap by presenting a high-quality curated dataset in the Hindi-English code-mixed language. The dataset includes 12,698 YouTube comments and replies, with each comment annotated under two-level categories, first as optimistic and pessimistic, and then into different types at second level based on the content. The inter-annotator agreement in the dataset is found to be 0.84 for the first subtask, and 0.79 for the second subtask, indicating the reasonably high quality of annotations. Different algorithmic models are explored for the task of automatic detection of the misogynistic attitude expressed in the comments, with the mBERT model giving best performance on both subtasks (reported macro average F1 scores of 0.59 and 0.52, and weighted average F1 scores of 0.66 and 0.65, respectively). The analysis and results suggest that the dataset can be used for further research on the topic and that the developed algorithmic models can be applied for automatic detection of misogynistic attitude in social media conversations and posts.

Sentiment analysis of the Hamas-Israel war on YouTube comments using deep learning

Sentiment analysis aims to classify text based on the opinion or mentality expressed in a situation, which can be positive, negative, or neutral. Therefore, in the world, a lot of opinions are available on various social media sites, which must be gathered and analyzed to assess the general public’s opinion. Finding and monitoring comments, as well as manually extracting the information contained in them, is a difficult task due to the vast diversity of ideas on YouTube. Identifying public opinion on war topics is crucial for offering insights to opposing sides based on popular opinion and emotions about the ongoing war. To address the gap, we build a model on YouTube comment sentiment analysis of the Hamas-Israel war to determine public opinion. In this study, we address the gaps by developing a deep learning-based approach for sentiment analysis. We have collected 24,360 comments from popular YouTube News Channels including BBC, WION, Aljazeera, and others about the Hamas-Israel War using YouTube API and Google spreadsheet and labeled them by linguistic experts into three classes: positive, negative, and neutral. Then, textual comments were preprocessed using natural language processing (NLP) techniques, and features were extracted using Word2vec, FastText, and GloVe. Moreover, we have used the SMOTE data balancing technique and used different data splits, but the 80/20 train-test split ratio has the highest accuracy. For classification model building, commonly used classification algorithms LSTM, Bi-LSTM, GRU, and Hybrid of CNN and Bi-LSTM were applied, and their performance is compared. As a result, the Hybrid of CNN and Bi-LSTM with Word2vec achieved the highest performance with 95.73% accuracy for comments classifications.

Making sense of ambivalence: audience perceptions and uses of Ben Shapiro as an alternative political commentator

ABSTRACT Alternative Political Commentators (APCs) have gained prominence on digital platforms as new opinion leaders to politically engaged young adults. This study responds to a growing demand for an audience-focused exploration of perceptions and use practices of what has been described as reactionary digital media. We specifically examine the case of Ben Shapiro, a leading conservative voice on YouTube, employing a mixed-methods approach, triangulating computational analyses of YouTube comments (n = 711,909) with in-depth interviews with young (18–33) daily Shapiro viewers based in Belgium (n = 15). Positioning Shapiro as an ambivalent online political figure, our study conceptualizes the two primary roles he fulfills for his audiences: (1) the rational articulate and non-emotional news provider, and (2) the affective witty and sometimes rude entertainer who skillfully ‘destroys’ opponents in so-called YouTube drama. Within their everyday life context, we reveal how audiences, in a likewise ambivalent manner, oscillate between casual use of Shapiro the entertainer and structured use of Shapiro the news provider. Through a reconstruction of Shapiro's dual role, our contribution suggests his style, particularly his voice, as a central quality through which audiences navigate Shapiro's ambivalence in their sense-making practices of him as an Alternative Political Commentator.