Promoting engagement with social fact-checks online

Social corrections, wherein social media users correct one another, are an important mechanism for debunking online misinformation. But users who post misinformation only rarely engage with social corrections, instead typically choosing to ignore them. Here, we investigate how the social relationship between the corrector and corrected user affect the willingness to engage with corrective, debunking messages. We explore two key dimensions: (i) partisan agreement with, and (ii) social relationships between the user and the corrector. We conducted a randomized field experiment with Twitter users and a conceptual replication survey experiment with Amazon Mechanical Turk workers in which posts containing false news were corrected. We varied whether the corrector identified as a Democrat or Republican; and whether the corrector followed the user and liked three of their tweets the day before issuing the correction (creating a minimal social relationship). Surprisingly, we did not find evidence that shared partisanship increased a user’s probability of engaging with the correction. Conversely, forming a minimal social connection significantly increased engagement rate. A second survey experiment found that minimal social relationships foster a general norm of responding, such that people feel more obligated to respond – and think others expect them to respond more – to people who follow them, even outside the context of misinformation correction. These results emphasize social media’s ability to foster engagement with corrections via minimal social relationships, and have implications for effective, engaging fact-check delivery online.

PENERAPAN TEXT MINING UNTUK MELAKUKAN CLUSTERING DATA TWEET AKUN BLIBLI PADA MEDIA SOSIAL TWITTER MENGGUNAKAN K-MEANS CLUSTERING

Social media is computer-based technology that facilitates the sharing of ideas, thoughts, and information through the building of virtual networks and communities. Twitter is one of the most popular social media in Indonesia which has 78 million users. Businesses rely heavily on Twitter for advertising. Businesses can use these types of tweet content as a means of advertising to Twitter users by Knowing the types of tweet content that are mostly retweeted by their followers . In this study, the application of Text Mining to perform clustering using the K-means clustering method with the best number of clusters obtained from the Silhouette Coefficient method on the @bliblidotcom Twitter tweet data to determine the types of tweet content that are mostly retweeted by @bliblidotcom followers. Tweets with the most retweets and favorites are discount offers and flash sales, so Blibli Indonesia could use this kind of tweet to conduct advertising on social media Twitter because the prize quiz tweets are liked by the @bliblidotcom Twitter account followers.

COVID-19 Related Sentiment Analysis Using State-of-the-Art Machine Learning and Deep Learning Techniques

The coronavirus disease 2019 (COVID-19) pandemic has influenced the everyday life of people around the globe. In general and during lockdown phases, people worldwide use social media network to state their viewpoints and general feelings concerning the pandemic that has hampered their daily lives. Twitter is one of the most commonly used social media platforms, and it showed a massive increase in tweets related to coronavirus, including positive, negative, and neutral tweets, in a minimal period. The researchers move toward the sentiment analysis and analyze the various emotions of the public toward COVID-19 due to the diverse nature of tweets. Meanwhile, people have expressed their feelings regarding the vaccinations' safety and effectiveness on social networking sites such as Twitter. As an advanced step, in this paper, our proposed approach analyzes COVID-19 by focusing on Twitter users who share their opinions on this social media networking site. The proposed approach analyzes collected tweets' sentiments for sentiment classification using various feature sets and classifiers. The early detection of COVID-19 sentiments from collected tweets allow for a better understanding and handling of the pandemic. Tweets are categorized into positive, negative, and neutral sentiment classes. We evaluate the performance of machine learning (ML) and deep learning (DL) classifiers using evaluation metrics (i.e., accuracy, precision, recall, and F1-score). Experiments prove that the proposed approach provides better accuracy of 96.66, 95.22, 94.33, and 93.88% for COVISenti, COVIDSenti_A, COVIDSenti_B, and COVIDSenti_C, respectively, compared to all other methods used in this study as well as compared to the existing approaches and traditional ML and DL algorithms.

Forecasting the next revolution: food technology’s impact on consumers' acceptance and satisfaction

PurposeIn a sector that needs to satisfy a fast-increasing population, advancements like cultivated meat and bio-circular economy are basic to sustain the industry and the society. As innovations are key for economic and social progress, it is crucial to understand consumers' position on this matter.Design/methodology/approachBased on text data mining, 7,030 tweets were collected and organised into 14 different food-related topics. Of the total, 6 of these categories were positive, 5 were negative and 3 were neutral.FindingsIn total, 6 categories related to food technologies were positively perceived by Twitter users, such as innovative solutions and sustainable agriculture, while 5 like the virtual dimensions of the industry or crisis-related scenarios were negatively perceived. It is remarkable that 3 categories had a neutral sentiment, which gives ground to improvement before consumers have a negative opinion and consequently will be more complicated to change their minds.Originality/valueTechnological innovations are becoming predominant in the food industry. The SARS-CoV-2 pandemic has made the sector improve even faster. Traditional methods needed to be substituted and technologies such as robots, artificial intelligence, blockchain and genetics are here to stay.

‘Without white people, the animals will go!’: COVID-19 and the struggle for the future of South African conservation

This article examines the potential for online activism to contest hegemonic neoliberal conservation models in South Africa, using the Covid-19 crisis as a window onto discursive struggle. National lockdown measures during the pandemic sent the vital tourism sector of an already fragile economy into deep crisis. Neoliberal and militarized conservation models, with their reliance on international travel, are examined as affected by a conjunctural crisis, the meaning of which was contested by a broad range of social actors in traditional and on social media. In 30 online news videos, racial hierarchies of land ownership and conservation labour geographies are reproduced and legitimated, as is a visual vocabulary of conservation as equivalent with guns, boots, and anti-poaching patrols. Here, hope is represented as residing in the increased privatization of public goods, and the extraction of value from these goods in the form of elite, luxury consumption. In a corpus of posts on Twitter corpus, on the other hand, significant counter-hegemonic resistance to established neoliberal conservation models is in evidence. In their replies to white celebrity conservationist Kevin Pietersen, critical South African Twitter users offer a contrasting vision of hope grounded in anti-racist equality, a rejection of any special human-animal relations enjoyed by Europeans, and an articulation of a future with land justice at its centre. The analysis supports the idea that in the “interregnum” between hegemonic social orders, pathways towards transformed futures may be glimpsed as “kernels of truth” in discursive struggles on social media.

Mediterranean Diet Social Network Impact along 11 Years in the Major US Media Outlets: Thematic and Quantitative Analysis Using Twitter

Background: Media outlets influence social attitudes toward health. Thus, it is important that they share contents which promote healthy habits. The Mediterranean diet (MedDiet) is associated with lower cardiovascular disease risk. Analysis of tweets has become a tool for understanding perceptions on health issues. Methods: We investigated tweets posted between January 2009 and December 2019 by 25 major US media outlets about MedDiet and its components as well as the retweets and likes generated. In addition, we measured the sentiment analysis of these tweets and their dissemination. Results: In total, 1608 tweets, 123,363 likes and 48,946 retweets about MedDiet or its components were analyzed. Dairy (inversely weighted in MedDiet scores) accounted for 45.0% of the tweets (723/1608), followed by nuts 19.7% (317/1608). MedDiet, as an overall dietary pattern, generated only 9.8% (157/1608) of the total tweets, while olive oil generated the least number of tweets. Twitter users’ response was quantitatively related to the number of tweets posted by these US media outlets, except for tweets on olive oil and MedDiet. None of the MedDiet components analyzed was more likely to be liked or retweeted than the MedDiet itself. Conclusions: The US media outlets analyzed showed reduced interest in MedDiet as a whole, while Twitter users showed greater interest in the overall dietary pattern than in its particular components.

The ideology of media. Measuring the political leaning of Spanish news media through Twitter users’ interactions

The news media have a strong influence on people’s perception of reality. But despite claims to objectivity, media organizations are, in general, politically biased (Patterson & Donsbach, 1996; Gaebler, 2017). The link between news media outlets and political organizations has been a critical question in political science and communication studies. To assess the closeness between the news media and particular political organizations, scholars have used different methods such as content analysis, undertaking surveys or adopting a political economy view. With the advent of social networks, new sources of data are now available to measure the relationship between media organizations and parties. Assuming that users coherently retweet political and news information (Wong, Tan, Sen & Chiang, 2016), and drawing on the retweet overlap network (RON) method (Guerrero-Solé, 2017), this research uses people’s perceived ideology of Spanish political parties (CIS, 2020) to propose a measure of the ideology of news media in Spain. Results show that scores align with the result of previous research on the ideology of the news media (Ceia, 2020). We also find that media outlets are, in general, politically polarized with two groups or clusters of news media being close to the left-wing parties UP and PSOE, and the other to the right-wing and far-right parties Cs, PP, and Vox. This research also underlines the media’s ideological stability over time.

Analysis of the Twitter discourse in the 2019 electoral debates in Spain: a comparative algorithmic study

This article analyzes and compares the following of Twitter users during the two electoral debates of the general elections in Spain in April and November 2019. Through the collection of the official hashtags #ElDebateDecisivo (970,706 tweets) and #DebateElectoral (821,521) respectively from 9 am on the day of the debate until 2 am the following day, we analyzed the polarity and basic emotions of the messages posted on the social network using algorithms with R software. A network theory study was also carried out to determine each account’s affiliation to each group. The results show a polarization in the network, with well-defined groups with hardly any relationship with other groups of different ideologies. It is also observed that the entry of a new player, Vox, into the second debate completely alters the rest of the center-right parties, which end up seeing it from a much more negative perspective. This entry does not involve major changes among the left-wing parties, but it does mean an increase in fear.

“Retweet for More”: The Serialization of Porn on the Twitter Alter Community

This article examines the notion of seriality in the context of the Filipino alter community, a network of Twitter users producing, distributing, and consuming pornographic images. The alter community is prominent among Filipino gay men who satisfy their need for sexual arousal, collective identity, and validation of their sexuality in the alter community. Seriality is influenced by technological features and affordances of a media platform. In the case of Twitter, the platform’s short form formats and real-time content generation fosters a particular kind of seriality. This essay analyzes data from online observations, content analysis of tweets and profiles, and interviews and is informed by theories on seriality, gay sexuality, and Internet studies. In situating seriality within the context of gay amateur porn economy, this article argues that serial pornography is instrumental in satisfying both present and long-standing affective, sexual, and social needs of gay men. These needs, this essay claims, stem from long history of minoritization of homosexuality. As Twitter renders older tweets ephemeral and quantifies social engagement, seriality enables gay men to satisfy the aforementioned needs longer. Furthermore, this essay proposes that serial porn on Twitter brings new insights to how seriality is conceived. Serial porn images are strategically and carefully constructed narratives of sexual encounters aimed at garnering higher social engagement and validation. Thus, serial narratives can resolve present and urgent affective tensions and needs that unravel within an ongoing life narrative rather than working toward supporting a plausible ending, as seen in other serial forms. This article contributes to an understanding of how pornographic images and serial narratives fit into consumerist culture and how platforms exploit long-standing affective needs of sexual minorities to ensure extended production and consumption of contents.