YouTube Data Research Articles

An automated approach to health misinformation monitoring on YouTube

Abstract Background YouTube is a social media platform associated with large viewership but little research into its role in the propagation of online health misinformation. This study proposes an automated pipeline to facilitate the collection and analysis of health misinformation on YouTube. Methods The pipeline relies on Python and the Youtube Data API. A preliminary test of the proposed pipeline was conducted using two videos from the channel “@BobbyParrish” (5.55M subscribers, 1.5K videos). The pipeline was used to extract two videos with large view counts and comparable like and comment counts. This extraction includes the transcript of the respective videos and engagement metrics. All the comment threads under the videos are also collected with the reply structure preserved. Then, the pipeline employs NLTK’s SentimentIntensityAnalyzer to score each comment for sentiment polarity and classify into positive, negative, or neutral. The pipeline generates visualizations of the sentiment distribution and a frequency-based word cloud of emojis extracted from the text. Results The proposed pipeline passed the test satisfactorily. It was able to retrieve channel statistics and metrics associated with the videos on the channel. It also successfully extracted the transcript and complete comments of the videos while preserving the integrity of the reply structure found on YouTube. Automated analyses of the data resulted in comprehensive and accessible visualizations. Conclusions The proposed work has the potential to facilitate large-scale studies into the propagation of health misinformation on YouTube. Moreover, it can be used by public health officials to rapidly address viral videos spreading health misinformation through social inoculation. Future work includes integrating topic modelling and automatic classification of health misinformation in the analysis portion of the pipeline. Key messages • The pipeline offers public health officials and researchers a rapid tool to identify and analyze health misinformation on YouTube, facilitating timely interventions. • The pipeline enhances the ability to monitor and respond to evolving public health misinformation trends, by automating the extraction and sentiment analysis of YouTube data.

Public views on open data health research in Switzerland: Implications for research and policy

Abstract Background The increasing volume of publicly available data offers health researchers opportunities to explore public sentiment through open data research on issues such as vaccination hesitancy and fake news propagation. To ensure ethical conduct and maintain public trust, assessing public perceptions of open data research in healthcare is crucial. Methods We conducted 10 focus groups across the German, French, and Italian-speaking regions of Switzerland. We presented participants with real-world examples of open data research in healthcare and guided discussions using a semi-structured format. The topic areas were: (1) using Twitter data to assess public opinion on gene-editing technology, (2) assessment of health policy documents, (3) using Twitter data to predict individual health status and (4) using YouTube data to assess public sentiment on health policies. We assessed our findings using a thematic analysis approach. Results Gathering insights from 75 citizens, four major themes emerged: (1) Expectations towards actors and open data research, such as using research findings for societal benefit, and ensuring transparency in data use through informed consent; (2) Supportive measures including communication strategies to raise awareness and inform the public about the use of publicly available data for health research; (3) Concerns about data reuse for purposes beyond the study’s objectives, especially for financial gain, and about data validity and privacy, particularly for sensitive health data; and (4) Mitigative measures to minimize harm, such as through the involvement of external oversight committees. Conclusions Our findings indicate public support for open data research in healthcare, provided that specific expectations are met. Developing a guiding framework for legitimate open data research in healthcare is a valuable next step, with a focus on enhancing public awareness through communication campaigns and providing oversight measures to foster public trust. Key messages • Open data research in healthcare relies on public data use without explicit consent, which can disconnect the research community from society. • We found that public support for open data research in healthcare is generally present, however it is also conditional on communication and policy efforts addressing their concerns.

Exploring Natural Language Processing through an Exemplar Using YouTube.

There has been a growing emphasis on data across various health-related fields, not just in nursing research, due to the increasing volume of unstructured data in electronic health records (EHRs). Natural Language Processing (NLP) provides a solution by transforming this unstructured data into structured formats, thereby facilitating valuable insights. This methodology paper explores the application of NLP in nursing, using an exemplar case study that analyzes YouTube data to investigate social phenomena among adults living alone. The methodology involves five steps: accessing data through YouTube's API, data cleaning, preprocessing (tokenization, sentence segmentation, linguistic normalization), sentiment analysis using Python, and topic modeling. This study serves as a comprehensive guide for integrating NLP into nursing research, supplemented with digital content demonstrating each step. For successful implementation, nursing researchers must grasp the fundamental concepts and processes of NLP. The potential of NLP in nursing is significant, particularly in utilizing unstructured textual data from nursing documentation and social media. Its benefits include streamlining nursing documentation, enhancing patient communication, and improving data analysis.

Detection of Misinformation Related to Pandemic Diseases using Machine Learning Techniques in Social Media Platforms

INTRODUCTION: The advent of the COVID-19 pandemic has brought with it not only a global health crisis but also an infodemic characterized by the rampant spread of misinformation on social media platforms. OBJECTIVES: In response to the urgent need for effective misinformation detection, this study presents a comprehensive approach harnessing machine learning and deep learning techniques, culminating in ensemble methods, to combat the proliferation of COVID-19 misinformation on Facebook, Twitter, Instagram, and YouTube. METHODS: Drawing from a rich dataset comprising user comments on these platforms, encompassing diverse COVID-19- related discussions, our research applies Support Vector Machine (SVM), Decision tree, logistic regression, and neural networks to perform indepth analysis and classification of comments into two categories: positive and negative information. The innovation of our approach lies in the final phase, where we employ ensemble methods to consolidate the strengths of various machine learning and deep learning algorithms. This ensemble approach significantly improves the model’s overall accuracy and adaptability. RESULTS: Experimental results underscore the efficacy of our methodology, showcasing marked improvements in detection performance compared to individual models. After applying ensemble learning, we achieve an accuracy of 91% for Facebook data, 79% for Instagram data, 80% for Twitter data and 95% for YouTube data. CONCLUSION: Our system not only aids in curbing the dissemination of COVID-19 misinformation but also provides a robust framework for addressing misinformation across various contexts on social media platforms.

유튜브 댓글 분석을 통한 클래식 음악 시청자 반응 연구

This study analyzed Korean-language comments on YouTube videos of pianist Lim Yunchan’s performance of Rachmaninoff’s Piano Concerto No. 3 during the 2022 Van Cliburn International Piano Competition finals, exploring domestic viewers’ reactions and emotional perceptions of classical music. The research methodology involved selecting only Korean comments collected via the YouTube Data API from June 20, 2022, to December 1, 2023, refining the data, and conducting keyword frequency analysis, LDA Topic Modeling, and sentiment analysis using R. The analysis indicated that viewers expressed deep emotional resonance and admiration for the artistic excellence of Lim’s performance through the identified keywords. The LDA Topic Modeling yielded three themes: ‘the Van Cliburn Competition’, ‘viewer responses’, and ‘the bright future of K-Classic’. Although the sentiment analysis showed some limitations, predominantly positive responses were observed. This study provides substantive data on how viewing classical music performances on YouTube can elicit emotional resonance and admiration for artistic excellence in viewers. Additionally, it confirmed that YouTube plays a crucial role in enhancing the accessibility of classical music and serving as a conduit for appreciation and communication. This research contributes to understanding the current landscape of Korea’s classical music consumption and offers insights into the consumption patterns of classical music in the digital media era.

YOUTUBE COMMENTS SCRAPING AND SENTIMENT ANALYSIS

The Social Media Sentiment Analysis web application is a powerful tool designed for content creators on various social media platforms, including YouTube. This application provides an intuitive interface for extracting and analyzing comments from YouTube videos, enabling content creators to gain valuable insights into the sentiment expressed by their viewers. By entering the YouTube video URL and an email address, users can harness the capabilities of this application to gain a comprehensive understanding of how their audience perceives their content. Leveraging the YouTube Data API, the application efficiently retrieves comments from the specified video. The application generates three files: comprehensive comments, positive comments, and negative comments, which are sent via email as Excel files. An interactive HTML table showcases sentiment distribution. This user-friendly application empowers content creators to track and enhance audience engagement on social media platforms, such as YouTube, through data-driven decision-making. Key Words: Social Media Sentimet Analysis , web application ,Youtube , analyzing comments , sentiment expressed , positive comments , negative comments

A Snapshot of COVID-19 Vaccine Discourse Related to Ethnic Minority Communities in the United Kingdom Between January and April 2022: Mixed Methods Analysis.

Existing literature highlights the role of social media as a key source of information for the public during the COVID-19 pandemic and its influence on vaccination attempts. Yet there is little research exploring its role in the public discourse specifically among ethnic minority communities, who have the highest rates of vaccine hesitancy (delay or refusal of vaccination despite availability of services). This study aims to understand the discourse related to minority communities on social media platforms Twitter and YouTube. Social media data from the United Kingdom was extracted from Twitter and YouTube using the software Netlytics and YouTube Data Tools to provide a "snapshot" of the discourse between January and April 2022. A mixed method approach was used where qualitative data were contextualized into codes. Network analysis was applied to provide insight into the most frequent and weighted keywords and topics of conversations. A total of 260 tweets and 156 comments from 4 YouTube videos were included in our analysis. Our data suggests that the most popular topics of conversation during the period sampled were related to communication strategies adopted during the booster vaccine rollout. These were noted to be divisive in nature and linked to wider conversations around racism and historical mistrust toward institutions. Our study suggests a shift in narrative from concerns about the COVID-19 vaccine itself, toward the strategies used in vaccination implementation, in particular the targeting of ethnic minority groups through vaccination campaigns. The implications for public health communication during crisis management in a pandemic context include acknowledging wider experiences of discrimination when addressing ethnic minority communities.

Beyond Word-Based Model Embeddings: Contextualized Representations for Enhanced Social Media Spam Detection

As social media platforms continue their exponential growth, so do the threats targeting their security. Detecting disguised spam messages poses an immense challenge owing to the constant evolution of tactics. This research investigates advanced artificial intelligence techniques to significantly enhance multiplatform spam classification on Twitter and YouTube. The deep neural networks we use are state-of-the-art. They are recurrent neural network architectures with long- and short-term memory cells that are powered by both static and contextualized word embeddings. Extensive comparative experiments precede rigorous hyperparameter tuning on the datasets. Results reveal a profound impact of tailored, platform-specific AI techniques in combating sophisticated and perpetually evolving threats. The key innovation lies in tailoring deep learning (DL) architectures to leverage both intrinsic platform contexts and extrinsic contextual embeddings for strengthened generalization. The results include consistent accuracy improvements of more than 10–15% in multisource datasets, unlocking actionable guidelines on optimal components of neural models, and embedding strategies for cross-platform defense systems. Contextualized embeddings like BERT and ELMo consistently outperform their noncontextualized counterparts. The standalone ELMo model with logistic regression emerges as the top performer, attaining exceptional accuracy scores of 90% on Twitter and 94% on YouTube data. This signifies the immense potential of contextualized language representations in capturing subtle semantic signals vital for identifying disguised spam. As emerging adversarial attacks exploit human vulnerabilities, advancing defense strategies through enhanced neural language understanding is imperative. We recommend that social media companies and academic researchers build on contextualized language models to strengthen social media security. This research approach demonstrates the immense potential of personalized, platform-specific DL techniques to combat the continuously evolving threats that threaten social media security.

An Assessment of YouTube Educational Video Quality Through Machine Learning

This paper presents a machine learning-based approach to assessing the quality of educational videos on YouTube. With the growing number of educational videos available on the platform, verifying efficacy and credibility has become increasingly important. To address this issue, we propose a framework that allows for automated evaluation of video content based on analytic parameters provided by the YouTube Data API. We look at features such as view count, comment polarity, channel subscriber count, like/dislike ratio, and comment count to capture various dimensions of video quality and engagement. We introduce our target variable as the "Educational Quality Score" (EQS), which measures a video's impact on education using the RACED model - Relevance, Accuracy, Clarity, Engagement, and Depth. Our method offers educators and content creators a tool to enhance their selection of quality educational YouTube videos.

The filter bubble generated by artificial intelligence algorithms and the network dynamics of collective polarization on YouTube: the case of South Korea

ABSTRACT This study examined the role of the ‘filter bubble,’ an algorithm-mediated YouTube video suggestion system, in political polarization and the presence of echo chamber patterns in public engagement. We examined the mechanism by which automated YouTube recommendations augment selective exposure to ideologically similar content and the network-based dynamics of collective polarization. We collected lists of videos recommended by conservative and progressive news media and the accompanying replies using YouTube application programming interfaces (APIs) embedded in YouTube Data Tools and Webometric Analyst 2.0. The study examined similarities in content of related videos and conversation networks between commenters, as well as the relationships between the videos, channels, and commenters. Almost half of the videos had content similar to the original videos offered by both conservative and progressive news media. The filter bubbles in progressive media were not as strong as those in conservative media. More than 30% of the videos recommended by progressive media were from legacy media, while this figure was 25% for conservative sources. This study has significant implications for reverse engineering studies because it collected data through APIs, which are neutral and can access YouTube servers without logging into individual IDs.

The nested relationality of perceived legitimacy: Mapping taste hierarchies with granular digital traces

The article has a double purpose. On the one hand, it contributes to theories of cultural legitimacy and classification. Based on data about consumers’ music evaluations, it shows that taste hierarchies are configured as nested and relational classificatory systems. Nested, because rank systems of symbolic value are collectively recognized, reproduced, and negotiated by consumers not only at the level of genres, but also at lower, nested levels – e.g., sub-genre, artist, single artwork; relational, because the value attributed to music by consumers is ordinarily assessed and constructed through analogies and comparisons, and partly depends on the classifier's relative position in the social space. On the other hand, this paper makes a key methodological contribution: by analyzing large amounts of YouTube data through computational methods and in combination with survey data, it illustrates how the granularity of digital traces can advance sociological research on cultural categories, meaning structures and symbolic imaginaries.

Selecting the foremost big data tool to optimize YouTube data in dynamic Fermatean fuzzy knowledge.

Big data pertains to extensive and intricate compilations of information that necessitate the implementation of proficient and cost-effective evaluation and analysis tools to derive insights and support decision making. The Fermatean fuzzy set theory possesses remarkable capability in capturing imprecision due to its capacity to accommodate complex and ambiguous problem descriptions. This paper presents the study of the concepts of dynamic ordered weighted aggregation operators in the context of Fermatean fuzzy environment. In numerous practical decision making scenarios, the term "dynamic" frequently denotes the capability of obtaining decision-relevant data at various time intervals. In this study, we introduce two novel aggregation operators: Fermatean fuzzy dynamic ordered weighted averaging and geometric operators. We investigate the attributes of these operators in detail, offering a comprehensive description of their salient features. We present a step-by-step mathematical algorithm for decision making scenarios in the context of proposed methodologies. In addition, we highlight the significance of these approaches by presenting the solution to the decision making problem and determining the most effective big data analytics platform for YouTube data analysis. Finally, we perform a thorough comparative analysis to assess the effectiveness of the suggested approaches in comparison to a variety of existing techniques.

Aspect-Based Sentiment Analysis for Afaan Oromoo Movie Reviews Using Machine Learning Techniques

Aspect-based sentiment analysis (ABSA) is the subfield of natural language processing that deals with essentially splitting data into aspects and finally extracting the sentiment polarity as positive, negative, or neutral. ABSA has been widely investigated and developed for many resource-rich languages such as English and French. However, little work has been done on indigenous African languages like Afaan Oromoo both at the document and sentence levels. In this paper, ABSA for Afaan Oromoo movie reviews was investigated and developed. To achieve the proposed objective, 2800 Afaan Oromoo movie reviews were collected from YouTube using YouTube Data API. Following the data preprocessing, predetermined aspects of the Afaan Oromoo movie were extracted and labeled into positive or negative aspects by domain experts. For implementation, different machine learning algorithms including random forest, logistic regression, SVM, and multinomial naïve Bayes in combination with BoW and TF-IDF were applied. To test and measure the proposed system, accuracy, precision, recall, and f1-score were used. In the case of random forest, the accuracy obtained in combination with both BoW and TF-IDF was 88%. Using the SVM, the accuracy generated with BoW and TF-IDF was 88% and 87%, respectively. Applying logistic regression, the accuracy generated with both BoW and TF-IDF was 87%. Using multinomial naïve Bayes, the accuracy generated in combination with both BoW and TF-IDF was 88%. To improve the optimal performance evaluation parameters, different hyperparameter tuning settings were applied. The implementation result shows that the optimal values of models’ performance evaluation parameters were generated using different hyperparameter tuning settings.

“That's why I never learned English from Indonesian teachers”:

This study aims to examine the extent to which native-speakerism (NS) is embedded in the comments responding to a YouTube video entitled “Salah Kursus Bahasa Inggris?- Seleb English” by a YouTuber named Sacha Stevenson. The researchers believe that native-speakerism, an ideology that creates a power imbalance favoring native speakers of English over nonnative speakers of English, is present in the video, in which the content creator scrutinizes Indonesian people’s English accents. However, this paper focuses on the comments responding to the video, since they can show to what extent NS is adopted by EFL speakers/learners in Indonesia. The data was retrieved using YouTube Data API and Python programming language, sorted using Microsoft Excel, and categorized by applying three reading steps into four levels which spans from 0 (no indication of native speakerism) to 3 (strong indication of native speakerism). The findings are presented descriptively and analyzed within the theoretical framework on NS. The results suggest that NS is present in the observed comments on all four levels, which suggests how deeply embedded the NS ideology within the community of Indonesian English language learners and speakers. Suggestions on how to counter this ideology are presented in conclusion.

A Study on the Precedence of Financial Markets Using YouTube Data

A Study on the Precedence of Financial Markets Using YouTube Data

Learning Analytics on YouTube Educational Videos: Exploring Sentiment Analysis Methods and Topic Clustering

The popularity of social media is continuously growing, as it endeavors to bridge the gap in communication between individuals. YouTube, one of the most well-known social media platforms with millions of users, stands out due to its remarkable ability to facilitate communication through the exchange of video content. Despite its primary purpose being entertainment, YouTube also offers individuals the valuable opportunity to learn from its vast array of educational content. The primary objective of this study is to explore the sentiments of YouTube learners by analyzing their comments on educational YouTube videos. A total of 167,987 comments were extracted and processed from educational YouTube channels through the YouTube Data API and Google Sheets. Lexicon-based sentiment analysis was conducted using two different methods, VADER and TextBlob, with the aim of detecting the prevailing sentiment. The sentiment analysis results revealed that the dominant sentiment expressed in the comments was neutral, followed by positive sentiment, while negative sentiment was the least common. VADER and TextBlob algorithms produced comparable results. Nevertheless, TextBlob yielded higher scores in both positive and negative sentiments, whereas VADER detected a greater number of neutral statements. Furthermore, the Latent Dirichlet Allocation (LDA) topic clustering outcomes shed light on various video attributes that potentially influence viewers’ experiences. These attributes included animation, music, and the conveyed messages within the videos. These findings make a significant contribution to ongoing research efforts aimed at understanding the educational advantages of YouTube and discerning viewers’ preferences regarding video components and educational topics.

YouTube Transcripts Word Frequency Measure

Many YouTube videos provide written audio transcripts which provide information on the language used on YouTube. One important measure relating to language usage is word frequency. Using student-developed software and libraries in R, Python, and Microsoft Excel, the transcripts of one million YouTube videos from the YouTube-8M data set were scraped and analyzed. The word frequency of the YouTube data set was shown to correlate with commonly used word frequency measures from established studies, such as the subtitle word frequency and the HAL word frequency.

Analysis of Agropreneurship Potential in the Middle of the COVID-19 Pandemic in Kupang City

This study examines agropreneurship in Kupang City and adjacent areas during the COVID-19 pandemic. The author uses qualitative descriptive methodologies to observe, interview, and document ten local agropreneurs. Newspaper, social media, and YouTube data supplemented the investigation. The results demonstrate that agropreneurs have product quality, reliable output, experience and love of farming, natural resource potential, and commercial and agricultural infrastructure. Agropreneurs benefit from rising demand for fresh veggies, close marketing networks, and reliable business even in times of crisis. However, this sector faces several weaknesses and threats, including inadequate farming equipment, limited capital, a lack of guidance for agropreneurs, limited land, and limited market information, as well as a lack of supporting institutions, high costs, competition, and PSBB-induced market decline. This research helps agropreneurs during crises like the COVID-19 pandemic understand entrepreneurship in Kupang City and the surrounding area. Results may vary by location and circumstance.

YouTube Comment Scraping and Sentiment Analysis Using Python and Machine Learning

YouTube has become a massive platform for video sharing and discussion, with millions of users expressing their thoughts and opinions through comments. For content producers, marketers, and academics, gleaning significant insights from these comments can yield useful data. This project explores the combination of machine learning and web scraping techniques to scrape YouTube comments and perform sentiment analysis. By leveraging machine learning algorithms, we aim to analyze sentiments, opinions, and trends within the vast amount of textual data generated on the platform. The process involves collecting comments using the YouTube Data API or web scraping libraries, followed by preprocessing steps to clean and transform the data. Next, Machine learning methods like Naive Bayes, SVM, or deep learning models are used to train sentiment analysis models. These approaches include Bag-of-Words, TF-IDF, and word embedding. Our ability to comprehend the overall emotion conveyed by viewers is subsequently made possible by the trained models, which are then utilized to anticipate the sentiment of fresh comments. Additionally, the ability to identify very favorable or negative remarks is made possible by sorting comments based on sentiment scores. It is essential to consider the complexities of language and contextual nuances when conducting sentiment analysis. For many players in the YouTube ecosystem, this technique does provide useful insights into audience feedback, content strategy, and data-driven decision-making.

Youtube Video TrendingAnalysis Based on Machine Learning

Social media platforms play an important role in commerce, entertainment, marketing, education, media and communication. YouTube has a large and active user base, making it the center of corporate digital marketing efforts. There are always videos that attract a lot of attention in a short period of time and become trending videos on YouTube, and these videos can be displayed as trending videos on YouTube and updated daily. In this article, we analyzed data on YouTube trending videos in the US region and analyzed the targets that captured the attention of users in a relatively short period of time. We conduct exploratory data analysis on each aspect to gain data insights and find statistical similarities between them to understand viewing patterns across video categories. We present our analysis by measuring, mining, analyzing, and doing ANOVA comparisons of four scales of different categories of likes, dislikes, opinions, and comments. In addition, the study compared the accuracy of three machine learning methods on YouTube data, which counts the number of views and viewer reactions of popular videos on YouTube.