Community extraction and visualization in social networks applied to Twitter

Abdelsadek, Youcef; Chelghoum, Kamel; Herrmann, Francine; Kacem, Imed; Otjacques, Benoît

doi:10.1016/j.ins.2017.09.022

Cited by 43 publications

(19 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Community identification is the stepping stone to understand the fundamental structural and semantic information in any network. Interconnected groups or communities can be identified based on the edge weight related to the number of times a tweet republished by Twitter users [22]. Abdelsadek et al [22] introduced a new algorithm called Tribase to analyze and identify communities from Twitter data.…”

Section: Literature Reviewmentioning

confidence: 99%

Analyzing Tweet Data to Identify the Impact of Demonetarization

Unnithan

Salloum

Shaalan

2021

Proceedings of International Conference on Emerging Technologies and Intelligent Systems

View full text Add to dashboard Cite

In this century, we have witnessed tremendous growth in the application of technology in our day-to-day life. One such life influencing factor is social media. In a manner or other, each individual's life is influenced by social media. Individuals and organizations rely more on social media to interact with people, acquire knowledge, promote business, gather information, news telecast, and for many other professional and personal purposes. Researchers use social media as one of the primary data sources for studies related to people's behavior and for various prediction purposes. This empirical study identifies the importance of social media data in recognizing any event's influence on the public. In October 2016 Indian government had demonetarized some active currency, and it created mixed reactions in public. For this research, tweet data was used to determine the impact of demonetarization on India's people. The study results demonstrate that tweet data can be relied on identifying or extracting general public opinions on any given topic or event.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Analyzing Tweet Data to Identify the Impact of Demonetarization

Unnithan

Salloum

Shaalan

2021

Proceedings of International Conference on Emerging Technologies and Intelligent Systems

View full text Add to dashboard Cite

show abstract

“…One of the important features in constructing and analyzing network is the detection of the groups or communities. Community detection falls in two categories [55], the first method relies on the structure of the network graph and mainly involves some variant of divisive [56] and agglomerative [57] algorithms. The second category, however, employs similarity matching between each couple of nodes to extract communities.…”

Section: Criminal Network Analysismentioning

confidence: 99%

“…The second category, however, employs similarity matching between each couple of nodes to extract communities. A variant of agglomerative algorithm ,called as TRIBASE [55] is demonstrated for the extraction of communities from twitter data,LOGANALYSIS [58], however utilized divisive algorithm [56] to detect communities. It employs force-directed node-link layout to constructs criminal networks from phone call records.…”

Section: Criminal Network Analysismentioning

confidence: 99%

An interactive human centered data science approach towards crime pattern analysis

Qazi

Wong

2019

Information Processing & Management

View full text Add to dashboard Cite

show abstract

“…They are asymmetrical: one may follow a user but not be followed back. Retweets, mentions in tweets and followers-followees' relationship are often the basis of Twitter sub-communities studies [Abdelsadek et al, 2018].…”

Section: Working With Twittermentioning

confidence: 99%

Invisible brokers: “citizen science” on Twitter

Tancoigne¹

2019

JCOM

View full text Add to dashboard Cite

Who speaks for “citizen science” on Twitter? Which territory of citizen science have they made visible so far? This paper offers the first description of the community of users who dedicate their online social media identity to citizen science. It shows that Twitter users who identify with the term “citizen science” are mostly U.S. science professionals in environmental sciences, and rarely projects' participants. In contrast to the original concept of “citizen science”, defined as a direct relationship between scientists and lay participants, this paper makes visible a third category of individual actors, mostly women, who connect these lay participants and scientists: the “citizen science broker”.

show abstract

Community extraction and visualization in social networks applied to Twitter

Cited by 43 publications

References 26 publications

Analyzing Tweet Data to Identify the Impact of Demonetarization

Analyzing Tweet Data to Identify the Impact of Demonetarization

An interactive human centered data science approach towards crime pattern analysis

Invisible brokers: “citizen science” on Twitter

Contact Info

Product

Resources

About