Facebook Comments Research Articles

The Thick Machine: Anthropological AI between explanation and explication

According to Clifford Geertz, the purpose of anthropology is not to explain culture but to explicate it. That should cause us to rethink our relationship with machine learning. It is, we contend, perfectly possible that machine learning algorithms, which are unable to explain, and could even be unexplainable themselves, can still be of critical use in a process of explication. Thus, we report on an experiment with anthropological AI. From a dataset of 175K Facebook comments, we trained a neural network to predict the emoji reaction associated with a comment and asked a group of human players to compete against the machine. We show that a) the machine can reach the same (poor) accuracy as the players (51%), b) it fails in roughly the same ways as the players, and c) easily predictable emoji reactions tend to reflect unambiguous situations where interpretation is easy. We therefore repurpose the failures of the neural network to point us to deeper and more ambiguous situations where interpretation is hard and explication becomes both necessary and interesting. We use this experiment as a point of departure for discussing how experiences from anthropology, and in particular the tension between formalist ethnoscience and interpretive thick description, might contribute to debates about explainable AI.

Language and Ethnic sentiments in Nigeria: Evidence from Facebook comments

Given the role of English as a language of wider communication in Nigeria, it is possible for people with different languages to interact without much linguistic barrier. The English language, therefore, facilitates communication. However, ethnic differences are still evident in the reactions and comments of people in different discourses which sometimes may lead to conflict and separation. A lot of studies exist which explore the roles of language in national development and unity and those that investigate patterns of self-assertiveness among ethnic groups characterised by ethnolinguistic vitality. However, patterns of ideological conflicts and solidarity based on ethnic affiliations have been under-researched. The present study relies on readers’ responses to Facebook comments to determine the role of language and ethnicity in solidarity formations in Nigeria. Data for this work was collected on the Facebook timelines of some socio-cultural groups in Nigeria. Ethnolinguistic Identity Theory and its revised standard version was adopted as the theory for the analysis. We discovered at the end of the work that ethnic bias reflects in the comment and response of people on Facebook. The use of linguistic and sociolinguistic features aid the ethnic inclusion and exclusion on Facebook.

Russian language in modern web space: dynamic processes and development trends

This article investigates new language trends in Internet communication. The goal was a comprehensive description of new features that appeared at every level of the language system functioning in the web space. Investigation of new systemic web phenomena has both relevance and perspectives, as the focus of literary language development has shifted from literary texts to web-based texts. The research material included Facebook posts and comments. The material was processed with stylistic methods (contextual, stylistic compatibility, interpretation, etc.). The synchronic analysis was accompanied with elements of diachronic commentary. The analysis also considered the normative aspect, yet the emphasis was made on the evolution of contemporary literary language influenced by digitalization and the growth of the Internet. The important factor in language transformation and development is realization of the creative function of the language in the user-generated content of the informal segment of the Internet. The multiple extralinguistic factors influencing Internet communication are described in details, but it is the creative function of the language and the features of new communication in the Internet space that are of primary importance for the development of the literary language in the Russian segment of the Internet. The study uses examples to prove the scientific hypothesis that new language phenomena on the Internet are not random, but on the contrary are systemic, as they are manifested at every language level. This allows drawing conclusions about the inevitability of transformation of the Russian language in the future, as the language will provide the communication of digital society that is already developing new ethic norms. Considering the trend on strengthening the legal frames for actions of state and transnational actors in the network space, the study of the Russian language and its trends in the Internet as one of the powerful means of soft power makes our study relevant for forming legislative mechanisms aimed at preserving Russian national interests in the international communication. The study is perspective, since it makes a significant contribution to preserving cultural and linguistic identity of Russian citizens in front of the growing international competition and uncertainty. In addition, being a linguistic study, this work deals with the issues of processing information with its increased speed and volume.

Amplifying retailers' sales with a hub's owned and earned social media: The moderating role of marketplace organic search

A hub firm is an agent that connects retailers to marketplace structures with the aim of selling products to final customers. Although social media is a decisive driver of consumer outcomes, it is unclear how a hub firm's earned and owned social media influences retailers' sales. Drawing on social identity theory, the authors propose a theoretical model that addresses the effects of blog comments, Facebook comments, fan following, and organic search sources (from a hub) on retailers' performance. In addition, the authors suggest that marketplace organic search moderates these main effects. Building on 4107 observations from 615 individual retailers across 26 months, the proposed model reveals that blog and Facebook comments, fan following, and hub organic search increase retailers' sales. Moreover, the results support the moderating role of marketplace organic search in amplifying these effects. Specifically, the effect of the interaction between marketplace organic search and hub organic search is significantly greater than that of the other examined interactions with Facebook or blog comments.

Nursing Perspectives on the Impacts of COVID-19: Social Media Content Analysis.

BackgroundNurses are at the forefront of the COVID-19 pandemic. During the pandemic, nurses have faced an elevated risk of exposure and have experienced the hazards related to a novel virus. While being heralded as lifesaving heroes on the front lines of the pandemic, nurses have experienced more physical, mental, and psychosocial problems as a consequence of the COVID-19 outbreak. Social media discussions by nursing professionals participating in publicly formed Facebook groups constitute a valuable resource that offers longitudinal insights.ObjectiveThis study aimed to explore how COVID-19 impacted nurses through capturing public sentiments expressed by nurses on a social media discussion platform and how these sentiments changed over time.MethodsWe collected over 110,993 Facebook discussion posts and comments in an open COVID-19 group for nurses from March 2020 until the end of November 2020. Scraping of deidentified offline HTML tags on social media posts and comments was performed. Using subject-matter expert opinions and social media analytics (ie, topic modeling, information retrieval, and sentiment analysis), we performed a human-in-a-loop analysis of nursing professionals’ key perspectives to identify trends of the COVID-19 impact among at-risk nursing communities. We further investigated the key insights of the trends of the nursing professionals’ perspectives by detecting temporal changes of comments related to emotional effects, feelings of frustration, impacts of isolation, shortage of safety equipment, and frequency of safety equipment uses. Anonymous quotes were highlighted to add context to the data.ResultsWe determined that COVID-19 impacted nurses’ physical, mental, and psychosocial health as expressed in the form of emotional distress, anger, anxiety, frustration, loneliness, and isolation. Major topics discussed by nurses were related to work during a pandemic, misinformation spread by the media, improper personal protective equipment (PPE), PPE side effects, the effects of testing positive for COVID-19, and lost days of work related to illness.ConclusionsPublic Facebook nursing groups are venues for nurses to express their experiences, opinions, and concerns and can offer researchers an important insight into understanding the COVID-19 impact on health care workers.

SOCIAL MEDIA ANALYSIS ON MALAY POLITICAL PARTIES IN MALAYSIA: STUDY ON THE ISSUES AND COMMENTS FACEBOOK

Social media is very important to disseminate and share information related to political issues to media users. Social media also provides space for media users to comment on political issues. Almost all political parties have their own 'page', as well as the candidates who are contesting, in addition to the content of the manifesto debate between the parties as well as the emotions of supporters and voters are uploaded on Facebook. This study identified the frequency, framing of issues and comments on the four Facebook of political parties. This study is to identify issues of common concern in Facebook Malay political parties and comments by Facebook users on the progress of the administration by the National Alliance government under the leadership of Tan Sri Muhyiddin Yassin. This study used qualitative methods to retrieve data from Facebook Malay political parties such as UMNO, PKR, PAS and BERSATU. Data collected from four political parties’ Malay Facebook starting 1 September 2020 to 31 December 2020. The researchers use Framing Theory to identify the issues that are discussed in social media. The analysis will be made according to the amount of frequency, type of issue, and form of comments discussed through the narrative approach. Based on data collected over the past four months, researchers found that the whole issue is being discussed by UMNO of 285, total 147 PAS, PKR as much as 122 and as many as 21 BERSATU while the issues discussed in the official Facebook account of Malay political party is criticism, elections, COVID-19, political, economic, social, governmental, educational and religious. The most discussed issue is political issues. As for the comment frequency trend, the satirical politeness form strategy was the highest involving comments on the four Facebook political parties.

Gender Inequalities and the Effects of Feminine Artworks on Public Spaces: A Dialogue

Feminist street art aims to transform patriarchal spaces into places of gendered resistance by asserting a feminist presence in the city. Considering this, as well as women’s social life, their struggle against lingering forces of patriarchy, and relating features of inequality (domestic violence), there was a feminist installation artwork by the young Kurdish artist Tara Abdulla that shook the city of Sulaimani in Iraqi Kurdistan on 26 October 2020. She had prepared a 4,800‐meter‐long washing line covered with the clothes of 99,678 Kurdish women who were survivors of sexual and gender‐based violence. They installed it along the busiest street of the city (Salim Street). She used this piece of feminine to express her reaction to the Kurdish society regarding, the abuse that goes on silently, behind closed doors. She also aimed towards normalizing women’s bodies. After the installation, she received many controversial reactions. As her artwork was a pioneering project in line with feminist issues in Kurdistan which preoccupied the city for quite a while, the aim of this article is to investigate the diverse effects of her work on the current dialogue regarding gender inequality in the Kurdish society. To do this, we used the research method of content analysis on big data (Facebook comments) to investigate the public reactions of a larger number of locals. The Feminine effectively exposed some of the deep‐rooted cultural, religious, and social barriers in addressing gender inequalities and silent sexual violence issues in the modern Kurdish patriarchal society.

Detecting Arabic Spam Reviews in Social Networks Based on Classification Algorithms

Reviews or comments that users leave on social media have great importance for companies and business entities. New product ideas can be evaluated based on customer reactions. However, this use of social media is complicated by those who post spam on social media in the form of reviews and comments. Designing methodologies to automatically detect and block social media spam is complicated by the fact that spammers continuously develop new ways to leave their spam comments. Researchers have proposed several methods to detect English spam reviews. However, few studies have been conducted to detect Arabic spam reviews. This article proposes a keyword-based method for detecting Arabic spam reviews. Keywords or Features are subsets of words from the original text that are labelled as important. A term's weight, Term Frequency–Inverse Document Frequency (TF-IDF) matrix, and filter methods (such as information gain, chi-squared, deviation, correlation, and uncertainty) have been used to extract keywords from Arabic text. The method proposed in this article detects Arabic spam in Facebook comments. The dataset consists of 3,000 Arabic comments extracted from Facebook pages. Four different machine learning algorithms are used in the detection process, including C4.5, kNN, SVM, and Naïve Bayes classifiers. The results show that the Decision Tree classifier outperforms the other classification algorithms, with a detection accuracy of 92.63%.

A Pragmatic Study of Humor in Iraqi Facebook Comments

The main goal of this study is to determine how comments are made by Iraqis on Facebook (a social media platform) to express humor and to discover whether these comments follow specific linguistic principles or not. There are millions of humorous comments on different types of posts, but only political posts were chosen in this research because of the importance of these posts. In the writer’s view, the politics of Iraq is greatly important as it dictates much of the situation that people currently live in. This means that there is also a lot of engagement by a lot of persons in Iraq with politics using humor, and there are therefore a large number of political posts using humor. This study relied on a specific method in analyzing data (namely comments selected from Facebook). 28 comments were selected for analysis by determining whether they follow the maxims of cooperative principles on the one hand and whether they follow any form of breaking of cooperative principles from another aspect. The arguments of Attardo were proven where he said that a person cannot be considered uncooperative in the conversation just because he said something funny or tried to be funny (Attardo, 2001). Moreover, the results showed that two forms of maxims of cooperative principle are followed several times, which are the maxims of relation and manner. It also showed that the least principle that is followed is the maxim of quality. There were also instances where maxims were not observed. It was found that the question of whether there would be flouting and violation of rules in the comments is most dependent on the commenter.

The Arguments of the COVID-19 Vaccines Opponents on Facebook in Poland: Textual Analysis Study

Abstract Background Social media allow users to quickly spread information and opinions. Unfortunately, it is often a place of anti-vaxxers activity, who create content that spreads easily. This situation leads to an increase in vaccine hesitancy and may result in outbreaks of infectious diseases. We wanted to find and characterize what negative arguments against the COVID-19 vaccines Facebook users create and how the popularity of the allegations against vaccines changes over time. Methods We followed the posts published on Facebook by the biggest Polish media. We have selected the highest commented events related to the registration and introduction of the COVID-19 vaccines. Then, we analyzed user comments related to those events and established the main themes of anti-vaccine comments. Using this list of topics, we categorized 3414 comments and checked the frequency of comments from given categories and their variability over time. Results The arguments of vaccine opponents about the COVID-19 vaccines can be divided into 12 categories. Seven of them also apply to other vaccines but five types are COVID-19' specific. Two new arguments say that vaccines were not properly tested or do not exist. The third topic mentions the history of the swine flu vaccine and the following narcolepsy cases. The fourth category suggests that vaccine against COVID-19 existed before the pandemic. The last argument says that no one takes responsibility for the side effects of the vaccine. The frequency of arguments from a given category varies over time. We also noticed that, while the comments were mostly negative, the reactions were positive. Conclusions Our codebook of anti-vaccine topics can help public health professionals better understand social media content. Real-time monitoring of social media is important because the popularity of certain arguments on Facebook changes rapidly over time but early recognition of social doubts allows for targeted interventions. Key messages Online anti-vaccine comments on the COVID-19 vaccines can be divided into 12 topic categories. The frequency of Facebook comments against COVID-19 vaccines from a given topic category varies over time.

Harnessing social listening to explore consumer cognitive bias: implications for upstream social marketing

PurposeThe purpose of this paper is to examine how upstream social marketing can benefit from using social media commentary to identify cognitive biases. Using reactions to leading media/news publications/articles related to climate and energy policy in Australia, this paper aims to understand underlying community cognitive biases and their reasonings.Design/methodology/approachSocial listening was used to gather community commentary about climate and energy policy in Australia. This allowed the coding of natural language data to determine underlying cognitive biases inherent in the community. In all, 2,700 Facebook comments were collected from 27 news articles dated between January 2018 and March 2020 using exportcomments.com. Team coding was used to ensure consistency in interpretation.FindingsNine key cognitive bias were noted, including, pessimism, just-world, confirmation, optimum, curse of knowledge, Dunning–Kruger, self-serving, concision and converge biases. Additionally, the authors report on the interactive nature of these biases. Right-leaning audiences are perceived to be willfully uninformed and motivated by self-interest; centric audiences want solutions based on common-sense for the common good; and left-leaning supporters of progressive climate change policy are typically pessimistic about the future of climate and energy policy in Australia. Impacts of powerful media organization shaping biases are also explored.Research limitations/implicationsThrough a greater understanding of the types of cognitive biases, policy-makers are able to better design and execute influential upstream social marketing campaigns.Originality/valueThe study demonstrates that observing cognitive biases through social listening can assist upstream social marketing understand community biases and underlying reasonings towards climate and energy policy.

Age is Nothing but a Number: Ben 10s, Sugar Mummies, and the South African Gender Order in the Daily Sun's Facebook Page.

Stories about “Ben10” relationships between older women and their younger male lovers appear regularly in the Daily Sun, South Africa’s most popular tabloid newspaper. Daily Sun readers, who are typically township residents, engage vociferously over the rights and wrongs of such relationships on the tabloid’s Facebook page, and alternatively berate or support the older, working class women who feature in them. These women could be understood as “postfeminist” insofar as they are financially independent and sexually autonomous. Their actions echo those of the independent township women in the mid 20th century who, resisting patriarchal apartheid social engineering, brewed beer and rented rooms in order to assert their financial and sexual independence. In both cases, these women’s bold actions confront local hetero-patriarchal norms and call into question an ideal local patriarchal gender order. However, the meanings that are made by the readers of such women in Ben10 relationships today also reflect a social context characterised by a contestation over the meaning of rights, high rates of unemployment, gender-based violence and HIV, factors that curtail a premature diagnosis of postfeminist identity. Drawing on a textual analysis of several articles and their Facebook comments, we argue that any assessment of postfeminism in southern spaces must account for how historical and contextual factors such as these constrain the reach of global postfeminism.

Enhancing advanced pharmacy practice experiences through the use of Web 2.0 technologies

Background and purposeWeb 2.0 technologies have been leveraged to enhance learning experiences. However, limited data exists about implementing Web 2.0 into pharmacy education and within experiential learning. Educational activity and settingTwo adult internal medicine advanced pharmacy practice experiences (APPEs) applied Web 2.0 technologies including Google (Alphabet, Inc.), Dropbox (Dropbox, Inc.), Facebook (Facebook, Inc.), WordPress (WordPress Foundation), and ClassDojo (ClassDojo, Inc.) with the primary purpose of enhancing student learning, with specific purposes for each technology including improvements in writing, reflection, and time-management skills. An analysis of the use of Web 2.0 technologies included comparing student and preceptor evaluations, mapping learning outcomes to assessments, and evaluating student engagement with the technologies, blog statistics, survey data, and application utilization. FindingsFrom 2017 to 2019, 40 students were engaged with Web 2.0 technologies as a component of their APPE. Student and preceptor evaluations remained relatively unchanged compared to evaluations before using Web 2.0. Students maintained high levels of engagement across applications including 2928 Facebook comments, 4016 “likes", 280 blog posts, and 158 blog comments. Survey results revealed that students perceived that Facebook and blogging helped improve overall learning and communication skills meeting important learning outcomes. SummaryThe integration of two APPEs with Web 2.0 technologies enhanced learning and achieved learning outcomes for students on their adult acute care rotation.

‘Just put it in perspective’: the perception of sexual voyeurism and violence in Singapore evaluated through Facebook comments

ABSTRACT There is scant research about sexual violence and attitudes towards it in Singapore. This study seeks to understand if Singapore has a rape-supportive culture, by examining how sexual violence is conceptualized, including the rising phenomenon of technology-enabled sexual violence. Facebook comments in response to mainstream media reporting of a well-known case of sexual voyeurism in 2019 were analysed. The data suggest that gender role expectations create an environment in which sexual violence is enabled and male perpetrators are absolved, and in which women are blamed for failing to avoid victimization. Gendered expectations also shape normative understandings of sexual behaviours, though the digital elements of voyeurism complicate understandings of violence and harm, inviting conceptualization of violence that goes beyond the element of physical contact. Commentators who resisted gender norms and scripts discussed violence in terms of interference with one's autonomy. Generally though, the frames of reference discovered in this analysis drew heavily on state norms and narratives and it is the state that can play a critical role in shifting mindsets to combat sexual violence.

Cascading Activation Revisited: How Audiences Contribute to News Agendas Using Social Media

Social media have become conduits through which audiences can challenge elites in media and politics. Recent updates to cascading activation, originally developed to explain how frames flowing from powerful figures gain public dominance, give greater theoretical scope for audiences to exert influence. Yet empirical understanding of how and in what circumstances this happens with respect to agenda-setting—another core media effect—is not well-developed, especially given the affordances of digital technologies. We address this gap by connecting theorization on cascades to developments in intermedia agenda-setting. Specifically, we analyze the dynamics surrounding the perceived reluctance by ARD-aktuell, the newsroom of Germany’s public broadcasting consortium, to use its prime-time broadcast “Tagesschau” to report the arrest of a refugee accused of murdering a German woman in December 2016. By presenting finely grained timelines linking content analysis of 5,409 Facebook comments with Tagesschau editorial responses and parallel media coverage of this event, we contribute further conditions under which audience-informed cascades may occur: notably, when publicly funded news organizations are involved, and the issue at stake invokes both domestic and international aspects which sustain disagreement.

Social media reactions of nurses to the documentary Stacey Dooley: On the Psych Ward

Background/Aims Mental health nursing is becoming a more transparent discipline. Increasingly, documentaries have provided the general public with insights regarding these therapeutic ward environments. The opinions of staff working in such places is important for ensuring the accuracy of the information, and the usefulness of what is publicly aired. This study explored the social media comments of nursing staff (as the experts) who viewed the Stacey Dooley: On the Psych Ward documentary. Methods Social media (Facebook and Twitter) were searched for comments on the documentary 3 weeks after the documentary was aired. In total, 4008 Facebook comments and 604 tweets were downloaded and assessed. Comments that did not relate to the documentary were excluded. A total of 31 Facebook comments and 54 tweets were used for analysis. Results Some evidence of criticism towards the presenter was found, as well as the use of an award-winning hospital as a non-representative – and unrealistic – example of psychiatric care. In general, healthcare staff felt that the documentary was useful for informing the general public, as well as students. Conclusions Documentaries such as this one that capture the realities of working on mental health wards have educational merit.

Self-Expression in the Cyber World: Challenges for a Woman

Apart from offering a platform to express opinions, social networking sites also enable people to maintain anonymity and express hatred. Women, particularly strong and opinionated ones, often fall prey to such revulsion. This investigation explores why and how women’s self-expression is curtailed in the virtual domain. To answer this question, thematic analysis has been carried out of Facebook comments and messages received by an Indian woman over a period of two years. Findings indicate that men responding to women’s online self-expression can fall into any of three emergent categories: self-proclaimed well-wishers, admirers turned abusers and the toxically masculine. While the first group silences women discreetly and typically by moral policing or invading women’s personal space, the latter two groups do so more blatantly. However, the three groups share a common patriarchal bias, believing that self-expression is a masculine privilege and women who try to democratise this privilege are cultural deviants.

Sentiment Analysis on Bengali Facebook Comments To Predict Fan's Emotions Towards a Celebrity

In this present era, sentiment analysis is considered as one of the most rapidly growing fields of computer science study. It is a text mining technique which is automated and determines the emotion of a text. A text can be divided into many emotions using sentiment analysis. Since there are some studies on emotion analysis in the Bangla language, it is regarded as a key research area in the field of analyzing Bangla language. This paper works with five different emotions and those are Happy, Sad, Angry, Surprise and Excited. Apart from these emotions our paper also deals with two categories, such as Abusive and Religious. We proposed a method of machine learning technique which is the SVM algorithm to extract these five individual emotions from Bangla text.

An Examination of Verbal Aggression in Politically-Motivated Digital Discourse

Verbal aggression in digital discourse has emerged as a substantial focus of interest for scholars wishing to examine how conflicts begin, unfold and end on Twitter, YouTube, blogs, and WhatsApp. However, despite all the scholarly attention that Facebook has received since its origin, verbal aggression on Facebook is still relatively under-researched. This paper examines verbal aggression online in the political discourse of Congo-Brazzaville Facebook users. More specifically, quantitative along with qualitative analyses of a dataset of 9,330 Facebook comments were jointly carried out. One critical finding is that explicit aggressive comments are overwhelmingly pervasive and on the increase, pointing to the conclusion that historical, social, sociolinguistic, and political factors are to a larger extent instigators of verbal aggression on Facebook. Furthermore, users employ different strategies to express or intensify verbal aggression, favoring explicit expressions of aggression such as insult and abuse over others like teasing.

Experiencing the Peer Feedback Activities with Teacher’s Intervention through Face-to-Face and Asynchronous Online Interaction: The Impact on Students’ Writing Development and Perceptions

The objectives of this study were to compare the impact of peer feedback implementation with teacher involvement through training in the classroom and asynchronous online communication on the quality of students' writing revisions, as well as to investigate students' perceptions of peer feedback activities. Twenty-five students participated in the experimental study. Eleven students were willingly to be interviewed. Inferential statistical analysis was used to interpret the quantitative data collected from students’ essay writing scores. Meanwhile, the data obtained through observations and interviews was interpreted using qualitative coding analysis. The results of the inferential statistical analysis revealed that peer feedback activities conducted through asynchronous online interactions had more significant effects compared to those conducted face to face on students’ writing revision. Further, after conducting a thematic analysis, six themes emerged: 1) peer feedback activities could increase students’ autonomy in learning, 2) the teacher's involvement in peer feedback activities was beneficial in terms of improving the consistency of feedback and revision, 3) peer feedback through asynchronous online interactions gave extra time to produce more beneficial comments, 4) peer feedback activities through asynchronous online interactions gave more chances to become a writing audience, 5) communicating via Facebook made the students feel awkward, and 6) recorded feedback via Facebook comments was more beneficial for students’ revision. The implication of the research is that teachers of English needs to consider asynchronous online interactions for students’ writing revision when teaching writing.