Reconstruction and analysis of Twitter conversation graphs

Cogan, P.; Andrews, Matthew; Bradonjic, Milan; Kennedy, W. Sean; Sala, Alessandra; Tucci, Gabriel

doi:10.1145/2392622.2392626

Cited by 48 publications

(58 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It should be noted that, in contrast to the case of user networks, a user may appear as different nodes in a network of posts. Networks of posts have been studied in Twitter (Kumar et al 2010;Kwak et al 2010;Bakshy et al 2011;Cogan et al 2012), Facebook (Sun et al 2009;Cheng et al 2014), blogs (Leskovec et al 2007b;McGlohon et al 2007;Götz et al 2009), Flickr (Cha et al 2009), discussion threads (Gómez et al 2008;Kumar et al 2010;Gómez et al 2011;Wang et al 2012;Gómez et al 2013), and e-mail (Liben-Nowell and Kleinberg 2008;Golub and Jackson 2010;Wang et al 2011).…”

Section: Introductionmentioning

confidence: 99%

Reply trees in Twitter: data analysis and branching process models

Nishi

Takaguchi

Oka

et al. 2016

Soc. Netw. Anal. Min.

View full text Add to dashboard Cite

Structure of networks constructed from mentioning relationships between posts in online media may be valuable for understanding how information and opinions spread in these media. We crawled Twitter to collect tweets and replies to construct a large number of so-called reply trees, each of which was rooted at a tweet and joined by replies. Consistent with the previous literature, we found that the empirical trees were characterized by some long path-like reply trees, large star-like trees, and long irregular trees, although their frequencies were not high. We tested several branching process models to explain the empirical frequency of these types of reply trees as well as more basic quantities such as the distributions of the size and depth of the reply tree. Based on our modeling results, we suggest that the in-degree of the tweet that initiates a reply tree (i.e., the number of times that the tweet is directly mentioned by other reply posts) may play an important role in forming the global shape of the reply tree.

show abstract

Section: Introductionmentioning

confidence: 99%

Reply trees in Twitter: data analysis and branching process models

Nishi

Takaguchi

Oka

et al. 2016

Soc. Netw. Anal. Min.

View full text Add to dashboard Cite

show abstract

“…Inspired by the approach taken by Cogan et al [7], this study consists of two main steps: the data collection phases and the graph construction. The data collection phase runs iteratively to obtain reply chains, process them and store them in a database.…”

Section: Methodsmentioning

confidence: 99%

An Evaluation of Performance and Competition in Customer Services on Twitter

Albishry

Crick

Tryfonas

et al. 2018

Companion of the the Web Conference 2018 on the Web Conference 2018 - WWW '18

View full text Add to dashboard Cite

This is the final published version of the article (version of record). It first appeared online via ACM at https://dl.acm.org/citation.cfm?id=3191631 . Please refer to any applicable terms of use of the publisher. University of Bristol -Explore Bristol Research General rightsThis document is made available in accordance with publisher policies. Please cite only the published version using the reference above. ABSTRACTWith an increasing number of consumers using social media platforms to share both their satisfaction and displeasure about the products and services they use every day, organisations with a customer service focus are recognising the importance of rapidand genuine -online engagement with their customers. In turn, consumers increasingly judge organisations on the quality of customer service and degree of responsiveness to online queries. This paper presents an extensible framework for evaluating direct engagements of customer service teams with customers on Twitter. Furthermore, this framework provides the capability to measure and analyse indirect engagement with industry sector rivals, especially their patterns, frequency and intensity. By applying graph analysis to these Twitter interactions, our framework generates various analytical measures and visual representations, exemplified through a case study based on seven major UK telecoms companies. With a dataset consisting of 15,000 tweets and 3,500 user profiles, the results provide sustained evidence for indirect engagements between business rivals, with customer queries acting as a trigger for intense competition between companies based in the same industry sub-domain.

show abstract

“…Given that 11% of the tweets across our data-sets were written in vernacular 3 , we chose not to use off-the-shelf Sentiment Analysis tools. Instead, building upon the features proposed in [5], we train a binary classifier (Support Vector Machine).…”

Section: Users and Opinionsmentioning

confidence: 99%

“…However, majority of the existing literature [3] focus on studying these conversations in isolation. These works highlight the importance of studying the overall structure that emerges in Social Media due to an Event.…”

Section: Introductionmentioning

confidence: 99%

Mining Twitter Conversations around E-commerce Promotional Events

Mathew

Unnikrishnan

Chakraborty

et al. 2016

Proceedings of the 19th ACM Conference on Computer Supported Cooperative Work and Social Computing Companion

View full text Add to dashboard Cite

With Social Media platforms establishing themselves as the de facto destinations for their customers' views and opinions, brands around the World are investing heavily on invigorating their customer connects by utilizing such platforms to their fullest. In this paper, we develop a novel technique for mining conversations in Twitter by weaving together all conversations around an event into one unified graph (Conversation Graph, henceforth). The structure of the Conversation Graph emerges as a variant of the BOWTIE structure (dubbed ASKEWBOWTIE henceforth) as a result of the complex communication patterns amongst these players. Finally, we investigate the structural properties of the ASKEWBOWTIE structure to understand the configuration of the components and their temporal evolution.

show abstract

Reconstruction and analysis of Twitter conversation graphs

Cited by 48 publications

References 11 publications

Reply trees in Twitter: data analysis and branching process models

Reply trees in Twitter: data analysis and branching process models

An Evaluation of Performance and Competition in Customer Services on Twitter

Mining Twitter Conversations around E-commerce Promotional Events

Contact Info

Product

Resources

About