Filters








251 Hits in 3.3 sec

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

Arkaitz Zubiaga, Elena Kochkina, Maria Liakata, Rob Procter, Michal Lukasik, Kalina Bontcheva, Trevor Cohn, Isabelle Augenstein
2018 Information Processing & Management  
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.  ...  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  ...  stances observed around rumours in social media.  ... 
doi:10.1016/j.ipm.2017.11.009 fatcat:z7hea76bzvajdhvnlurxlxrrni

Bi-Directional Recurrent Neural Ordinary Differential Equations for Social Media Text Classification [article]

Maunika Tamire, Srinivas Anumasa, P.K. Srijith
2021 arXiv   pre-print
Our experiments demonstrate that RNODE and Bi-RNODE are effective for the problem of stance classification of rumours in social media.  ...  Sequence classification models based on recurrent neural networks (RNN) are popular for classifying posts that are sequential in nature.  ...  Discourse-aware information and use it to model the dynamics of hidden representa- rumour stance classification in social media using sequential classifiers.  ... 
arXiv:2112.12809v1 fatcat:aqcho23wgndprfmxanb66z5wqa

Towards Explainable Fact Checking [article]

Isabelle Augenstein
2021 arXiv   pre-print
These automatic methods are often content-based, using natural language processing methods, which in turn utilise deep neural networks to learn higher-order features from text in order to make predictions  ...  This development has spurred research in the area of automatic fact checking, from approaches to detect check-worthy claims and determining the stance of tweets towards claims, to methods to determine  ...  “Discourse-aware rumour stance classification in social media using sequential classifiers”.  ... 
arXiv:2108.10274v2 fatcat:5s4an6irezcjfmvvhmiaeqarh4

From Clickbait to Fake News Detection: An Approach based on Detecting the Stance of Headlines to Articles

Peter Bourgonje, Julian Moreno Schneider, Georg Rehm
2017 Proceedings of the 2017 EMNLP Workshop: Natural Language Processing meets Journalism  
We present a system for the detection of the stance of headlines with regard to their corresponding article bodies. The approach can be applied in fake news, especially clickbait detection scenarios.  ...  We want to contribute to the debate on how to deal with fake news and related online phenomena with technological means, by providing means to separate related from unrelated headlines and further classifying  ...  The setup of our system adheres to this scoring method, and hence applies several classifiers sequentially, as explained in Section 4.  ... 
doi:10.18653/v1/w17-4215 dblp:conf/emnlp/BourgonjeSR17 fatcat:slwupdd7crfhvdqko7tzf6a3ri

Mining social media for newsgathering: A review

Arkaitz Zubiaga
2019 Online Social Networks and Media  
Use of social media for newsgathering is however challenging, and suitable tools are needed in order to facilitate access to useful information for reporting.  ...  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.  ...  The best approach, by Enayet and El-Beltagy [99] , used a stance classification system to determine the stance of each post associated with a rumour, which are aggregated to determine the likely veracity  ... 
doi:10.1016/j.osnem.2019.100049 fatcat:dt63zddmqba7vc47cyjve37i5q

What goes on inside rumour and non-rumour tweets and their reactions: A Psycholinguistic Analyses [article]

Sabur Butt, Shakshi Sharma, Rajesh Sharma, Grigori Sidorov, Alexander Gelbukh
2021 arXiv   pre-print
In the descriptive line of works, where researchers have tried to analyse rumours using NLP approaches, there isnt much emphasis on psycho-linguistics analyses of social media text.  ...  In recent years, the problem of rumours on online social media (OSM) has attracted lots of attention. Researchers have started investigating from two main directions.  ...  context-aware rumour detection using a sequential classifier To answer these research questions, we used the PHEME-9 to detect rumours from the tweets divided into five news dataset, consisting  ... 
arXiv:2112.03003v1 fatcat:sxs657ycwrcfnc657okmopwouu

Hoax analyzer for Indonesian news using RNNs with fasttext and glove embeddings

Ryan Adipradana, Bagas Pradipabista Nayoga, Ryan Suryadi, Derwin Suhartono
2021 Bulletin of Electrical Engineering and Informatics  
The latter results show that fastText embedding is better than GloVe embedding in supervised text classification, along with BI-GRU + fastText yielding the best result.  ...  terms of metrics score when classifying news between three classes: fake, valid, and satire.  ...  LIAR dataset is also viable for stance classification, argument mining, topic modelling, rumour detection and political natural language processing (NLP) research [8] .  ... 
doi:10.11591/eei.v10i4.2956 fatcat:dbmdjoif6jgizalevolzh3papa

Sentiment Analysis for Fake News Detection

Miguel A. Alonso, David Vilares, Carlos Gómez-Rodríguez, Jesús Vilares
2021 Electronics  
The huge amount of news that is disseminated through social media makes manual verification unfeasible, which has promoted the design and implementation of automatic systems for fake news detection.  ...  This has led to sentiment analysis, the part of text analytics in charge of determining the polarity and strength of sentiments expressed in a text, to be used in fake news detection approaches, either  ...  stance classification) or not (open stance classification).  ... 
doi:10.3390/electronics10111348 fatcat:p34nbmtkzrcqrowu24nmu4axnq

Sequential Modelling with Applications to Music Recommendation, Fact-Checking, and Speed Reading [article]

Christian Hansen
2021 arXiv   pre-print
text semantics in order to automatically fact-check claims, or "speed read" text for efficient further classification.  ...  Sequential modelling entails making sense of sequential data, which naturally occurs in a wide array of domains.  ...  Discourse- aware rumour stance classification in social media using sequential classifiers. Informatino Processing & Management, 54(2):273-290.  ... 
arXiv:2109.06736v1 fatcat:xawmkvzhgng3vhhrs5xvwokqna

Global digital genre-communication forms in the process of flow to local Polish memosphere: the case of Facebook art memes

Anna Gumkowska, Piotr Toczyski
2016 Studies in Global Ethics and Global Education  
New digital genre-communication forms are exemplified by Facebook "art memes", which should be studied from two perspectives: literary research and social studies.  ...  We analysed the mechanisms generating specific genres in the digital network and described the phenomena which result in shaping new forms of modern communication genres.  ...  , rumours or jokes.  ... 
doi:10.5604/23920890.1215489 fatcat:lbulh7r2jzdw5cykikgog6y4d4

Semantic Representation and Inference for NLP [article]

Dongsheng Wang
2021 arXiv   pre-print
This thesis investigates the use of deep learning for novel semantic representation and inference, and makes contributions in the following three areas: creating training data, improving semantic representations  ...  Finally, in terms of inference learning, we propose a series of novel deep learning architectures that improve inference by using syntactic dependencies, by ensembling role guided attention heads, incorporating  ...  Discourse- aware rumour stance classification in social media using sequential classifiers. Informatino Processing & Management, 54(2):273-290.  ... 
arXiv:2106.08117v1 fatcat:qi3546wlhfd2xhqj3f776wa6km

Shallow features as indicators of English–German contrasts in lexical cohesion

Kerstin Kunz, Ekaterina Lapshinova-Koltunski, José Manuel Martínez Martínez, Katrin Menzel, Erich Steiner
2017 Languages in Contrast: International Journal for Contrastive Linguistics  
The shallow features analysed are: highly frequent words in texts, lexical density, standardized type-token-ratio, top-frequent content words of the language within individual registers and texts, and  ...  The results are interpreted relative to our hypotheses and related to the following properties of texts in terms of lexical cohesion: semantic variability, cohesive strength, number and length of nominal  ...  UIMA: an architectural approach to unstructured information processing in the corporate research environment. Natural Language Engineering, 10(3-4):327-348.  ... 
doi:10.1075/lic.16005.kun fatcat:p7pa2crm6rgkrfmsdf7m5265ea

COMPLETE ISSUE

Lectito Press Office
2018 Feminist Encounters: A Journal of Critical Studies in Culture and Politics  
Critical analysis of how gender discourses produce cultural identities and social practices within diverse lived realities is key to this change.  ...  We need to think more sharply in order to strategise well: as the discourses of conservatism renew and invigorate themselves, so we as feminist scholars need to be refining our amazonic swords in order  ...  I would like to specially thank Naznin Akter Banu for long discussions on South Asian feminist engagements with Development discourses.  ... 
doi:10.20897/femenc.201814 fatcat:azsnq4g62ba65jzrg7ieahgeei

Learning to Detect Few-Shot-Few-Clue Misinformation [article]

Qiang Zhang, Hongbin Huang, Shangsong Liang, Zaiqiao Meng, Emine Yilmaz
2021 arXiv   pre-print
Consequently, a large volume of false textual information has been disseminating for a long time since the prevalence of social media.  ...  Few-shot-few-clue learning applies in this misinformation detection task when the number of annotated statements is quite few (called few shots) and the corresponding evidence is also quite limited in  ...  People react to a piece of statement by expressing their stances or emotions in social media posts.  ... 
arXiv:2108.03805v1 fatcat:cjndpclo2ra4hmqw2wm4262yvi

Stance characterization and detection on social media [article]

Abeer AlDayel, University Of Edinburgh, Walid Magdy, Bonnie Webber
2021
The current research on socio-political opinion mining on social media is still in its infancy.  ...  Second, we examine the multi-modal representation of stance on social media by evaluating multiple stance detection models using textual content and online interactions.  ...  The incorporation of stance helps in debunking rumours by using social media users' stances, supporting or denying a given claim.  ... 
doi:10.7488/era/1606 fatcat:nt7t6s52gffjdpzy7rjo6nvf74
« Previous Showing results 1 — 15 out of 251 results