Supporting the Use of User Generated Content in Journalistic Practice

Lecture Notes in Computer Science

Liakata

Procter

2017

Self Cite

223

116

Abstract. Tools that are able to detect unverified information posted on social media during a news event can help to avoid the spread of rumours that turn out to be false. In this paper we compare a novel approach using Conditional Random Fields that learns from the sequential dynamics of social media posts with the current state-of-the-art rumour detection system, as well as other baselines. In contrast to existing work, our classifier does not need to observe tweets querying the stance of a post to deem it a rumour but, instead, exploits context learned during the event. Our classifier has improved precision and recall over the state-of-the-art classifier that relies on querying tweets, as well as outperforming our best baseline. Moreover, the results provide evidence for the generalisability of our classifier.

Section: Introductionmentioning

confidence: 99%

Exploiting Context for Rumour Detection in Social Media

Lecture Notes in Computer Science

Liakata

Procter

2017

Self Cite

223

116

“…Finally -and importantly -instead of dealing with tweets as single units in isolation, we exploit the emergent structure of interactions between users on Twitter, building a classifier that learns the dynamics of stance in tree-structured conversational threads by exploiting its underlying interactional features. While these interactional features do not, in the final analysis, map directly onto those of conversation as revealed by Conversation Analysis [34], we argue that there are sufficient relational similarities to justify this approach [35]. The closest work is by Ritter et al [36] who modelled linear sequences of replies in Twitter conversational threads with Hidden Markov Models for dialogue act tagging, but the tree structure of the thread as a whole was not exploited.…”

Section: Related Workmentioning

confidence: 91%

Discourse-aware rumour stance classification in social media using sequential classifiers

Information Processing & Management

Kochkina

Liakata

et al. 2018

Self Cite

128

Rumour stance classification, defined as classifying the stance of specific social media posts into one of supporting, denying, querying or commenting on an earlier post, is becoming of increasing interest to researchers. While most previous work has focused on using individual tweets as classifier inputs, here we report on the performance of sequential classifiers that exploit the discourse features inherent in social media interactions or 'conversational threads'. Testing the effectiveness of four sequential classifiers -Hawkes Processes, Linear-Chain Conditional Random Fields (Linear CRF), Tree-Structured Conditional Random Fields (Tree CRF) and Long Short Term Memory networks (LSTM) -on eight datasets associated with breaking news stories, and looking at different types of local and contextual features, our work sheds new light on the development of accurate stance classifiers. We show that sequential classifiers that exploit the use of discourse properties in social media conversations while using only local features, outperform non-sequential classifiers. Furthermore, we show that LSTM using a reduced set of features can outperform the other sequential classifiers; this performance is consistent across datasets and across types of stances. To conclude, our work also analyses the different features under study, identifying those that best help characterise and distinguish between stances, such as supporting tweets being more likely to be accompanied by evidence than denying tweets. We also set forth a number of directions for future research.

“…When social media is used for newsgathering, however, it presents the challenge that the stream of updates flows much faster than a human can follow, with hundreds or even thousands of posts per minute, which makes it impossible for a human to keep track of everything that is being said. There is indeed the need to curate all these contents in such a way that the end user can follow [38,39,40]. Journalists are in great need of applications that facilitate newsgathering work [41].…”

Section: Social Media For Journalistsmentioning

confidence: 99%

Mining social media for newsgathering: A review

Online Social Networks and Media

2019

Self Cite

Social media is becoming an increasingly important data source for learning about breaking news and for following the latest developments of ongoing news. This is in part possible thanks to the existence of mobile devices, which allows anyone with access to the Internet to post updates from anywhere, leading in turn to a growing presence of citizen journalism. Consequently, social media has become a go-to resource for journalists during the process of newsgathering. Use of social media for newsgathering is however challenging, and suitable tools are needed in order to facilitate access to useful information for reporting. In this paper, we provide an overview of research in data mining and natural language processing for mining social media for newsgathering. We discuss five different areas that researchers have worked on to mitigate the challenges inherent to social media newsgathering: news discovery, curation of news, validation and verification of content, newsgathering dashboards, and other tasks. We outline the progress made so far in the field, summarise the current challenges as well as discuss future directions in the use of computational journalism to assist with social media newsgathering. This review is relevant to computer scientists researching news in social media as well as for interdisciplinary researchers interested in the intersection of computer science and journalism.