Search results

This study aims to construct a sentiment series generation method for danmu comments based on deep learning, and explore the features of sentiment series after clustering.

This study consisted of two main parts: danmu comment sentiment series generation and clustering. In the first part, the authors proposed a sentiment classification model based on BERT fine-tuning to quantify danmu comment sentiment polarity. To smooth the sentiment series, they used methods, such as comprehensive weights. In the second part, the shaped-based distance (SBD)-K-shape method was used to cluster the actual collected data.

The filtered sentiment series or curves of the microfilms on the Bilibili website could be divided into four major categories. There is an apparently stable time interval for the first three types of sentiment curves, while the fourth type of sentiment curve shows a clear trend of fluctuation in general. In addition, it was found that “disputed points” or “highlights” are likely to appear at the beginning and the climax of films, resulting in significant changes in the sentiment curves. The clustering results show a significant difference in user participation, with the second type prevailing over others.

Their sentiment classification model based on BERT fine-tuning outperformed the traditional sentiment lexicon method, which provides a reference for using deep learning as well as transfer learning for danmu comment sentiment analysis. The BERT fine-tuning–SBD-K-shape algorithm can weaken the effect of non-regular noise and temporal phase shift of danmu text.

This study argues that online user comments on social media platforms provide feedback and evaluation functions. These functions can provide services for the relevant departments of organizations or institutions to formulate corresponding public opinion response strategies.

This study considers Chinese universities’ public opinion events on the Weibo platform as the research object. It collects online comments on Chinese universities’ network public opinion governance strategy texts on Weibo, constructs the sentiment index based on sentiment analysis and evaluates the effectiveness of the network public opinion governance strategy adopted by university officials.

This study found the following: First, a complete information release process can effectively improve the effect of public opinion governance strategies. Second, the effect of network public opinion governance strategies was significantly influenced by the type of public opinion event. Finally, the effect of public opinion governance strategies is closely related to the severity of punishment for the subjects involved.

The theoretical contribution of this study lies in the application of image repair theory and strategies in the field of network public opinion governance, which further broadens the scope of the application of image repair theory and strategies.

This study expands online user comment research to network public opinion governance and provides a quantitative method for evaluating the effect of governance strategies.

The peer review history for this article is available at: https://publons.com/publon/10.1108/OIR-05-2022-0269

This study examines the relationship between streamers' product descriptions, customer comments and online sales and focuses on the moderating effect of streamer–viewer relationship strength.

Between June 2021 and April 2022, the structured data of 965 livestreaming and unstructured text data of 42,956,147 characters from two major live-streaming platforms were collected for the study. Text analysis and regression analysis methods were employed for data analysis.

First, the authors' analysis reveals an inverted U-shaped relationship between comment length and product sales. Notably, comment volume and comment emotion positively influence product sales. Furthermore, the semantic richness, emotion and readability of streamers' product descriptions also positively influence product sales. Secondly, the authors find that the strength of streamer–viewer relationship weakens the positive effects of comment volume and comment emotion without moderating the inverted U-shaped effect of comment length. Lastly, the strength of streamer–viewer relationship also diminishes the positive effects of emotion, semantics and readability of streamers' product descriptions on product sales.

This study is the first to concurrently examine the direct and interactive effects of user-generated content (UGC) and marketer-generated content (MGC) on consumer purchase behaviors in livestreaming e-commerce, offering a novel perspective on individual decision-making and cue utilization in the social retail context.

Vaccine hesitancy is a long-standing issue among both the general population and health communicators. This study aims to ascertain the inclination and the reasons for vaccine hesitancy by conducting content analysis and sentiment analysis of the perspectives expressed in comments on videos related to vaccine hesitancy uploaded from India on YouTube.

The assessment of the sentiments of the vaccine-hesitant population is done using Valence Aware Dictionary and sEntiment Reasoner sentiment analysis module implemented with Python’s NLTK library to automatically determine the sentiments of the comments. Manual content analysis was performed on 60.09% viewer comments randomly selected from the total comments in 238 videos on vaccine hesitancy originated from India and labelled each comment with labels “Anti”, “Pro”, “Confused”, “Not Applicable” and “Unrelated” labels.

The study found “Mistrust-Government policies”, “Fear-health related consequences”, “Mistrust-Scientific research”, “Vaccine effectiveness and efficacy” and “Misinformation/myths” as the top five determinants for vaccine hesitancy, whereas “Religious beliefs”, “Fear-Economic consequences”, “Side Effects- short-term” and “Fear-mode of administration” found to be the lesser cited reasons for vaccine hesitancy. However, the study also investigates changes in the inclination of Indian commenters towards vaccine hesitancy and revolving issues over time.

Public health policymakers and health communicators may find the study useful in determining vaccine hesitancy factors in India.

The originality of this study lies in its approach. To date, no sentiment analysis has been conducted on the content released on YouTube by Indian content creators regarding pro- and anti-vaccination videos. This inquiry seeks to fill this research gap.

The purpose of this study was to perform sentiment analysis and analyze the growth and popularity of Drupal, Joomla and WordPress on YouTube over a four-year period. This included identifying the most liked and commented videos for each content management system (CMS), ranking the CMSs based on the number of positive comments they received, and using natural language processing techniques to identify the top ten most frequently appearing words in videos about the CMSs.

The data for assessing the features of the videos of Drupal, WordPress and Joomla was extracted using Webometric Analyst version 4.4. with the help of the YouTube application programming interface key for videos on the selected CMSs uploaded from 2019 to 2022. The extraction of comments and sentiment analysis for the relevant videos was done using Mozdeh.

This study scrutinized 371, 234 and 313 videos of WordPress, Joomla and Drupal on YouTube. The findings reveal that there is a chronological growth of videos of the three CMSs in four years and till the present time, WordPress has the highest number of videos followed by Drupal and then Joomla. Regarding the ranking of highly liked videos, WordPress again wins the list with the highest number of likes in its videos followed by Drupal and then Joomla. For analyzing sentiments of the total comments extracted 123,409 for WordPress, 1,790 for Joomla and 1,783 for Drupal, respectively, WordPress receives the highest average positive comments followed by Drupal then Joomla. In top word frequency, the word “thank” highly occurs and viewers are asking for more tutorial videos.

To the best of the authors’ knowledge, this study is the first attempt for analyzing the sentiments of WordPress, Drupal and Joomla using Mozdeh software within the concerning period.

This study aims to investigate replies to the top 10 comments under Always “Like a Girl” YouTube femvertising video to gauge consumers’ responses regarding femvertising as well as relationships among commenters.

This study adopted a mixed research methods design. A user analysis and a qualitative content analysis were conducted to examine the replies of the top 10 comments with the most replies to reveal not only the topics but also relationships and patterns among those comments and commenters.

The user analysis found that across all the 10 comment-and-reply units, in 8 units, the user of the original primary comment, the conversation starter, was also the user who was targeted most often. The qualitative content analysis revealed four themes from the 10 comment-and-reply units: multilayered emotional responses, a gendered society, complex coexisting relationships and a melting pot.

The findings of this research offer significant extensions to the understanding of public sphere theory within the contemporary digital media landscape. By analyzing the nature of replies to digital advertisements, the study illuminates how various types of user engagement–whether it be inquiry, laudation, debate, or flame–play a critical role in shaping the digital public sphere.

The study underscores the importance for marketers to scrutinize both comments and replies to effectively utilize femvertising on social media, particularly YouTube. By understanding the emotional dynamics of user interactions, marketers can craft strategies that evoke positive responses and mitigate negative ones. Engaging with users who are open to changing their views or mediating discussions can also be beneficial, as can the use of AI tools to maintain focus on the content rather than on individual commenters. Such approaches can enhance the perception of femvertising campaigns and foster a more constructive dialogue within the social media space.

This study contributes to the literature by investigating the replies of comments, interactions, relationships and patterns among YouTube commenters that may generate valuable insights for advertisers and marketers to be aware of the possible issues and monitor the sentiment of commentaries, thus, developing effective strategies to better connect with consumers. This extends the understanding of public sphere theory in the contemporary digital media landscape.

The study aims to propose an instrument for measuring product-centeredness (i.e. the extent to which comment content is related to a product) using word embedding techniques as well as explore its determinants.

The study collected branded posts from 205 Instagram influencers and empirically examined how four factors (i.e. authenticity, vividness, coolness and influencer–product congruence) influence the content of the comments on branded posts.

Post authenticity and congruence are shown to have positive effects on product-centeredness. The interaction between coolness and authenticity is also significant. The number of comments or likes on branded posts is not correlated with product-centeredness.

In social media influencer marketing, volume-based metrics such as the numbers of likes and comments have been researched and applied extensively. However, content-based metrics are urgently needed, as fans may ignore brands and focus on influencers. The proposed instrument for assessing comment content enables marketers to construct content-based metrics. Additionally, the authors' findings enhance the understanding of social media users' engagement behaviors.

This paper aims to illustrate the extensive benefits of qualitative data analysis as a rarely undertaken process in post-occupancy evaluation surveys. As a result, there is limited evidence of what occupants say about their buildings, especially for operational parameters, as opposed to how they rate them. While quantitative analyses provide useful information on how workers feel about workplace operational factors, qualitative analyses provide richer information on what aspects of the workplace workers identify as influential to their comfort, well-being and productivity.

The authors analysed 6,938 comments from office buildings worldwide on workers’ perception of workplace operational factors: design, storage, needs, space at desks and storage in their work environments. These factors were analysed based on the buildings’ design intent and use, and the associated comments were coded into positive, negative and balanced comments. The authors used a combination of coding, descriptive analysis, content analysis and word cloud to dissect the comments.

The findings showed that whereas workers rated these operational factors favourably, there were significantly more negative comments about each factor. Also, the Chi-square test showed a significant association (p < 0.01) between the satisfaction scale and the type of comments received for all the operational factors. This means that when a factor is rated high in the satisfaction score (5–7), there were fewer negative and more positive comments and vice versa. The word cloud analysis highlighted vital aspects of the office environment the workers mostly commented on, such as open plan design, natural lighting, space and windows, toilets, facilities, kitchens, meeting room booking systems, storage and furniture.

This study highlights the importance of dissecting building occupants’ comments as integral to building performance monitoring and measurement. These emphasise the richness and value of respondents’ comments and the importance of critically analysing them. A limitation is that only 6,938 comments were viable for analysis because most comments were either incomplete with no meaning or were not provided. This underlines the importance of encouraging respondents to comment and express their feelings in questionnaire surveys. Also, the building use studies questionnaire data set presents extensive opportunities for further analyses of interrelationships between demographics, building characteristics and environmental and operational factors.

The findings from this study can be applied to future projects and facility management to maintain and improve office buildings throughout their life cycle. Also, these findings are essential in predicting the requirements of future workplaces for robust workplace designs and management.

The authors identified specific comments on the performance of workplaces across the globe, showing similarities and differences between sustainable, conventional, commercial and institutional buildings. Specifically, the analysis showed that office workers’ comments do not always corroborate the ratings they give their buildings. There was a significantly higher percentage of negative comments than positive comments despite the high satisfaction scores of the operational factors.

The purpose of this paper is to investigate the comment letters (CLs) in the standard-setting process of audits of less complex entities (LCEs). The objective is to gain insight into the overall picture of the CLs and to report on areas where comment providers agree or disagree with IAASB's Part 10.

A content analysis of 60 comment letter (CLs) was conducted to investigate the suggested additional Part 10 on audits of groups' financial statements in the proposed ISA for LCEs. Hence, this study examines three specific topics: (1) the views related to the use of the International Standard on Auditing (ISA) for LCEs for group audits in which component auditors are involved, (2) the proposed group-specific qualitative characteristics to describe the scope of group audits and, finally, (3) insights into the content of the proposed Part 10 and related conforming amendments. The Gioia method is used to provide a holistic approach to concept development of the arguments about the new Part 10.

The CLs stated that, while the proposed Part 10 has some weak points, it still provides a solid and practical structure within which to undertake an LCE group audit and a promising basis for further development. For instance, when discussing the improvements, the CLs stated that Part 10 should allow for more auditor judgment when determining when the involvement of component auditors renders a group audit complex. In addition, the CLs asserted that professional judgment should be engaged when considering the qualitative characteristics and the complexity of the group.

This study contributes to the very scarce research about the ISA for LCEs and the role of lobbying in shaping the audit standard-setting process.

Misinformation surrounding the Sustainable Development Goals (SDGs) has contributed to the formation of misbeliefs among the public. The purpose of this paper is to investigate public sentiment and misbeliefs about the SDGs on the YouTube platform.

The authors extracted 8,016 comments from YouTube videos associated with SDGs. The authors used a pre-trained Python library NRC lexicon for sentiment and emotion analysis, and to extract latent topics, the authors used BERTopic for topic modeling.

The authors found eight emotions, with negativity outweighing positivity, in the comment section. In addition, the authors identified the top 20 topics discussing various SDGs and SDG-related misbeliefs.

The authors reported topics related to public misbeliefs about SDGs and associated keywords. These keywords can be used to formulate social media content moderation strategies to screen out content that creates these misbeliefs. The result of hierarchical clustering can be used to devise and optimize response strategies by governments and policymakers to counter public misbeliefs.

This study represents an initial endeavor to gain a deeper understanding of the public’s misbeliefs regarding SDGs. The authors identified novel misbeliefs about SDGs that previous literature has not studied. Furthermore, the authors introduce an algorithm BERTopic for topic modeling that leverages transformer architecture for context-aware topic modeling.