scholarly journals Unified Representation of Twitter and Online News Using Graph and Entities

2021 ◽  
Vol 4 ◽  
Author(s):  
Munira Syed ◽  
Daheng Wang ◽  
Meng Jiang ◽  
Oliver Conway ◽  
Vishal Juneja ◽  
...  

To improve consumer engagement and satisfaction, online news services employ strategies for personalizing and recommending articles to their users based on their interests. In addition to news agencies’ own digital platforms, they also leverage social media to reach out to a broad user base. These engagement efforts are often disconnected with each other, but present a compelling opportunity to incorporate engagement data from social media to inform their digital news platform and vice-versa, leading to a more personalized experience for users. While this idea seems intuitive, there are several challenges due to the disparate nature of the two sources. In this paper, we propose a model to build a generalized graph of news articles and tweets that can be used for different downstream tasks such as identifying sentiment, trending topics, and misinformation, as well as sharing relevant articles on social media in a timely fashion. We evaluate our framework on a downstream task of identifying related pairs of news articles and tweets with promising results. The content unification problem addressed by our model is not unique to the domain of news, and thus can be applicable to other problems linking different content platforms.

2021 ◽  
Vol 16 (1) ◽  
pp. 95-97
Author(s):  
Sarah Bartlett Schroeder

A Review of: Evanson, C., & Sponsel, J. (2019). From syndication to misinformation: How undergraduate students engage with and evaluate digital news. Communications in Information Literacy, 13(2), 228-250. https://doi.org/10.15760/comminfolit.2019.13.2.6 Abstract Objective – To determine how new undergraduate students access, share, and evaluate the credibility of digital news. Design – Asynchronous online survey and activity. Setting – A small private, liberal arts college in the southeastern United States of America. Subjects – Participants included 511 incoming first-year college students. Methods – Using the Moodle Learning Management System, incoming first-year students completed a mandatory questionnaire that included multiple choice, Likert scale, open-ended, and true/false questions related to news consumption. Two questions asked students to identify which news sources and social networking sites they have used recently, and the next two questions asked students to define fake news and rate the degree to which fake news impacts them personally and the degree to which it impacts society. The end of the survey presented students with screenshots of three news stories and asked them to reflect on how they would evaluate the claim in the story, their confidence level in the claim, and whether or not they would share this news item on social media. The three items chosen represent certain situations that commonly cause confusion for news consumers: (a) a heading that does not match the text of the article, (b) a syndicated news story, and (c) an impostor URL and fake news story. Researchers coded the student responses using both preset and emergent codes. Main Results – Eighty-two percent of students reported using at least one social media site to access political news in the previous seven days. Students reported believing that fake news is a worrying trend for society, with 86% labelling it either a “moderate” or “extreme” barrier to society’s ability to recognize accurate information. However, they expressed less concern about their own ability to navigate an information environment in which fake news is prevalent, with 51% agreeing that it has only somewhat of an effect on their own ability to effectively navigate digital information. Of the three news items presented to them, students expressed the least confidence (an average of 1.55/4) and least interest in sharing (12%) the first news item, in which the heading does not match the text. However, only 14% of respondents noted this mismatch. In evaluations of the second item, an AP news item on the Breitbart website, 35% of students noted the website on which the article was found, but fewer noted that the original source is the Associated Press. Student responses to the third article, a fake news item from a website masquerading as an NBC website, show that 37% of students believed the source to come from a legitimate NBC source. Only 7% of students recognized the unusual URL, and 24% of respondents indicated that they might share this news item on social media. Conclusion – The study finds that impostor URLs and syndicated news items might confuse students into misevaluating the information before them, and that librarians and other instructors should raise awareness of these tactics.


2019 ◽  
Vol 5 (2) ◽  
pp. 205630511984750 ◽  
Author(s):  
Brooke E. Auxier ◽  
Jessica Vitak

With the influx of content being shared through social media, mobile apps, and other digital sources—including fake news and misinformation—most news consumers experience some degree of information overload. To combat these feelings of unease associated with the sheer volume of news content, some consumers tailor their news ecosystems and purposefully include or exclude content from specific sources or individuals. This study explores customization on social media and news platforms through a survey ( N = 317) of adults regarding their digital news habits. Findings suggest that consumers who diversify their online news streams report lower levels of anxiety related to current events and highlight differences in reported anxiety levels and customization practices across the political spectrum. This study provides important insights into how perceived information overload, anxiety around current events, political affiliations and partisanship, and demographic characteristics may contribute to tailoring practices related to news consumption in social media environments. We discuss these findings in terms of their implications for industry, policy, and theory.


2014 ◽  
Vol 2014 ◽  
pp. 1-23 ◽  
Author(s):  
A. Balali ◽  
H. Faili ◽  
M. Asadpour

User-generated texts such as comments in social media are rich sources of information. In general, the reply structure of comments is not publicly accessible on the web. Websites present comments as a list in chronological order. This way, some information is lost. A solution for this problem is to reconstruct the thread structure (RTS) automatically. RTS predicts a semantic tree for the reply structure, useful for understanding users’ behaviours and facilitating follow of the actual conversation streams. This paper works on RTS task in blogs, online news agencies, and news websites. These types of websites cover various types of articles reflecting the real-world events. People with different views participate in arguments by writing comments. Comments express opinions, sentiments, or ideas about articles. The reply structure of threads in these types of websites is basically different from threads in the forums, chats, and emails. To perform RTS, we define a set of textual and nontextual features. Then, we use supervised learning to combine these features. The proposed method is evaluated on five different datasets. The accuracy of the proposed method is compared with baselines. The results reveal higher accuracy for our method in comparison with baselines in all datasets.


2020 ◽  
Vol 58 (1) ◽  
pp. 5-21
Author(s):  
Nicoline van der Sijs

Abstract Research among twentieth-century Dutch and Flemish emigrants has shown that they usually gave up their mother tongue quickly, within two or three generations, after emigration. In the twenty-first century the situation of emigrants has changed drastically: due to the internet and social media it is much easier to keep in touch with the homelands. Does this have consequences for the preservation of the Dutch language and culture among emigrants? How much do emigrants value the Dutch language, culture and identity? These questions have been investigated in the pilot research ‘Vertrokken Nederlands ‐ Emigrated Dutch’, conducted by the Dutch Language Union and the Meertens Institute and led by the author of this article. The research has been conducted using a new methodology, employing social media and citizen scientists. This article describes the results of this first worldwide study of Dutch language, culture and identity among Dutch and Flemish emigrants. The main conclusion of the research is that for the vast majority of emigrants in the twenty-first century, the Dutch language and culture still play an important role in daily life, and the Dutch language is still widely used in the country of residence, especially within the family, in social media and in online news services.


2021 ◽  
Vol 5 (1) ◽  
Author(s):  
Rizzy Andika Al Fathan ◽  
Amin Aminudin

This study aims to see how the strategy of the indozone.id visual team in designing infographics on Instagram social media. The research statement proposed is how the strategy of the indozone.id visual team in designing infographics on Instagram social media? In this study using a qualitative descriptive method based on the constructivist paradigm. The research subjects were the Visual Team, Editors, and Followers of the indozone Instagram account. With the data collection techniques of observation, interviews and documentation conducted through key-information and informants, this study uses the Media Ecology theory from MC. Luhan. In its implementation, online media owners produce various elements in the news they make. Online news agencies are always prone to convey unverified information to the wider community which results in misperception and misinterpretation of news that has facts. Therefore the focus of this research is the strategy of the indozone.id visual team in designing infographics on social media Instagram. The results of this study can be seen that the strategies implemented by indozone.id include making infographics easy to understand, interesting titles, looking for news to be used as infographics, obstacles when making infographics. This strategy was carried out by the visual team in presenting the infographic. Keywords: Strategy, Online Media, Infographics, Instagram


2019 ◽  
Author(s):  
Mohammed Juma Zagood

It is increasingly interesting that one of the new focuses of translation studies is the translatability of the short posts on social media. Research in translating social media posts has recently received a greater attention among translation studies specialists. This paper looks firstly at Twitter as a growing social media networking and its language and, secondly, shedding some light on translation strategies used in translating English tweets into Arabic. Posts on Twitter, ‘tweets,’ by well-known figures are followed, translated, and reposted in other languages every day. Strategies used by Arab translators vary depending on the importance of the tweet as well as the ideology of the translator and the institutions they work for. This paper, therefore, investigates the translation strategies adopted by the Arab online news agencies, mentioned later, on their web pages in translating some tweets posted by the American President, Donald Trump in his first month of presidency. The analysis draws on Vinay and Darbelnet’s (1958/1995) model and Nida’s (1964) translation strategies.


2021 ◽  
Vol 26 (1) ◽  
pp. 149-157
Author(s):  
Natalia E. Rastorgueva ◽  
Yarileisy Barcelay Ramirez

The changes that have taken place in the work of Cuban news agencies during the digitalization of media production are analyzed. Over the past few years, they have been undergoing a process of transformation, changing their approaches to providing information and introducing new products. To study these processes, the authors resort to the digital platforms of two news agencies - Prensa Latina and Agencia Cubana de Noticias , as well as the online news portal Cubadebate . Comparative and analytical methods of research reveal the specific features of functioning of these media resources at the present moment. The authors conclude that despite the international isolation Cuba experienced for more than sixty years and relatively limited financial resources allocated for media development, the country's media market has entered a period of modernization. All the changes taking place will greatly expand the possibilities for integrating Cuban news agencies into global information processes.


Data mining and prediction systems have been the center of attraction since information retrieval came into existence. Most IT companies spend a lot of resources on such analysis and systems to improve their performance and generate more revenue depending on the nature of work that they do. Online News Feed Prediction System aims to provide an analysis and comparison of various prediction techniques by using different methods of implementation. UCI repository contains a collection of databases pertaining to different topics. News popularity in multiple social media is one such dataset containing information about news topics from different sources, sentiment analysis of title and headline, topic that they are related to, publishing date, popularity score in various social media platforms. Python, R and Weka have been used on this data set to implement data preprocessing, visualization and prediction techniques like Random Forest, Decision Tree and SVM. Moreover, there is dataset on the analysis of the score for every twenty minutes for the social media platforms chosen. Analysis on these platforms helps in developing a system to reach a wider audience. News agencies can use this system to increase their profit and visibility. This paper aims to realize the ways to obtain these results


Author(s):  
Meghan Lynch ◽  
Irena Knezevic ◽  
Kennedy Laborde Ryan

To date, most qualitative knowledge about individual eating patterns and the food environment has been derived from traditional data collection methods, such as interviews, focus groups, and observations. However, there currently exists a large source of nutrition-related data in social media discussions that have the potential to provide opportunities to improve dietetic research and practice. Qualitative social media discussion analysis offers a new tool for dietetic researchers and practitioners to gather insights into how the public discusses various nutrition-related topics. We first consider how social media discussion data come with significant advantages including low-cost access to timely ways to gather insights from the public, while also cautioning that social media data have limitations (e.g., difficulty verifying demographic information). We then outline 3 types of social media discussion platforms in particular: (i) online news article comment sections, (ii) food and nutrition blogs, and (iii) discussion forums. We discuss how each different type of social media offers unique insights and provide a specific example from our own research using each platform. We contend that social media discussions can contribute positively to dietetic research and practice.


Humaniora ◽  
2020 ◽  
Vol 11 (1) ◽  
pp. 13
Author(s):  
Abitassha Az Zahra ◽  
Eko Priyo Purnomo ◽  
Aulia Nur Kasiwi

The research aimed to explain the pattern of social communication on the issue of rejection of the PLTU Batang development policy. It used data on Twitter accounts involved in the rejection of the PLTU Batang development policy. In analyzing existing data, qualitative methods and social analysis networks were used. To see social networks in the rejection of the PLTU Batang development policy, the research used the NodeXL application to find out the patterns of social communication networks in #TolakPLTUBatang. From the results, it can be seen that in the dissemination of social networking information, the @praditya_wibby account is the most central account in the social network and has a strong influence on the social network. The @praditya_wibby account has a role in moving the community through Twitter to make a critical social movement. This means that in the current digital era, democracy enters a new form through the movement of public opinion delivery through social media. Besides, by encouraging the role of online news, the distribution of information becomes faster to form new perceptions of an issue. This is evident from the correlation network where the @praditya_wibby account has correlations with several compass online media accounts, tirto.id, okezonenews, vice, antaranews, BBCIndonesia, and CNN Indonesia.


Sign in / Sign up

Export Citation Format

Share Document