2018/01/16 by Abdallah El Ali, Ali, Abdallah El, Tim Claudius Stratmann +9
Computer Science · Physics and Astronomy · Social Sciences · #Computers and Society (cs.CY) #FOS: Computer and information sciences #H.5.3 #Misinformation and Its Impacts #Opinion Dynamics and Social Influence #Sentiment Analysis and Opinion Mining #Social and Information Networks (cs.SI)
paper · pdf · doi:10.48550/arxiv.1801.05802
openalex publication_date 2018/01/16 · openalex created_date 2022/10/04 · openalex updated_date 2026/07/28
This paper investigates bias in coverage between Western and Arab media on\nTwitter after the November 2015 Beirut and Paris terror attacks. Using two\nTwitter datasets covering each attack, we investigate how Western and Arab\nmedia differed in coverage bias, sympathy bias, and resulting information\npropagation. We crowdsourced sympathy and sentiment labels for 2,390 tweets\nacross four languages (English, Arabic, French, German), built a regression\nmodel to characterize sympathy, and thereafter trained a deep convolutional\nneural network to predict sympathy. Key findings show: (a) both events were\ndisproportionately covered (b) Western media exhibited less sympathy, where\neach media coverage was more sympathetic towards the country affected in their\nrespective region (c) Sympathy predictions supported ground truth analysis that\nWestern media was less sympathetic than Arab media (d) Sympathetic tweets do\nnot spread any further. We discuss our results in light of global news flow,\nTwitter affordances, and public perception impact.\n