We are pleased to invite you to our Wednesday Research Seminar. It will be held online on 21 October from 4pm via Microsoft team platform.
Wednesday Research Seminar Series was launched in 2008, and has featured more than 280 presentations to date. The seminars provide a forum for researchers to share their work. Presenters include faculty from Middlesex University Dubai and other universities in the United Arab Emirates, as well as researchers from other global institutions. Krishnadas and Supriya will deliver seminar on:
“Examination of Fake online content from a Viral perspective: An interplay of emotions, resonance, and sentiments”
Krishnadas Nanath, Supriya Kaitheri, Sonia Malik and Shahid Mustafa
With the growth of social media platforms, the consumption of online content has drastically changed. A report by the Jumpshot Tech Blog found that Facebook has 50% of the total traffic to fake news sites and 20% of total traffic to reputable websites (Jumpshot, 2016). This research takes up online news to examine fake content and develops a model that could automate fake news detection.
The authors of this research take up a dataset of news articles that are coded as fake and non-fake (manually code). They further use the concepts of virality and explore how content is made viral with the help of theories in the literature. The modeling is based on the premise that the prime intention of a fake news creator would be to make it go viral and attain the intended reach and clicks. Therefore, the variables that could make online content go viral are selected as the independent variables to predict it in the category of fake or not. The study selects four groups of variables for the machine learning modeling using logistic regression: Verbosity (word and sentence count), emotions (trust, joy, anger, anticipation, disgust, fear, sadness, and surprise), topic modeling, and resonance between title and article (sentiment match, positive and negative sentiments). The results revealed that positive emotions, longer articles, and high sentimental resonance between the title and the text led to lower chances of being a fake article. On the other hand, longer titles and content related to illegal activities led to higher chances of news being fake.
Krishnadas is currently the Assistant CPC and Associate Professor in Data Science (Computer Engineering and Informatics department) at Middlesex University Dubai. In his previous role @ Majid Al Futtaim (MAF), he was responsible for leading the efforts of enhancing Analytics and Data Science capabilities at MAF as the head of the School of Analytics. Before joining MAF, he was teaching Data Science, MIS, and Cloud Technologies at Middlesex University Dubai, Institute of Management Technology (IMT Dubai), and IIM Indore. He has executed several corporate training programs and Data Science consulting assignments with prestigious firms in UAE (PWC, Emirates NBD, Landmark Group, National Bank of Fujairah, PDO, UAE Exchange, and others). He received his Ph.D. from the Indian Institute of Management Kozhikode (IIM K), and his thesis covered the areas of Green IT (Sustainability Analytics) and Cloud Computing. His career started as a Computer Science engineer (B.Tech CSE), and he had successful professional experiences with Microsoft Research and Honeywell.
Supriya is currently working as a faculty in the Business school at Middlesex University Dubai campus. Before joining Middlesex, she completed her doctoral studies at the Indian Institute of Management Kozhikode, and the thesis was in the area of ICT for social development and e-Governance. She was also a Gold medalist in Computer Science and Engineering. She works in the areas of e-Governance, User Technology Readiness, Data Analytics, and Cloud Computing. She has special interests in the areas of Quantitative Research, Business Analytics, Social media Analytics, and Experimental Research.
Looking forward to seeing you at the seminar!