We summarize the state of progress in artificial intelligence as used for classifying misinforma- tion, or ’fake news’. Making a case for AI in an assistive capacity for factchecking, we briefly examine the history of the field, divide current work into ’classical machine learning’ and ’deep learning’, and for both, examine the work that has led to certain algorithms becoming the de facto standards for this type of text classification task.
In a practical experiment, we benchmark five common text classification algorithms - Naive Bayes, Logistic Regression, Support Vector Machines, Random Forests, and eXtreme Gradient Boosting - on multiple misinformation datasets, accounting for both data-rich and data-poor environments.
LIRNEasia Chair, Rohan Samarajiva shared a message with students in Sri Lanka who have completed their formal education on SLVLOG Good Vibes.
Intended for policymakers, technologists, educators and others, this international collection of 19 short stories delves into AI’s cultural impacts with hesitation and wonder.
Information collection (or data collection) is vital during an epidemic, especially for purposes such as contact tracing and quarantine monitoring. However, it also poses challenges such as keeping up with the spread of the infectious disease, and the need to protect personally identifiable information. We explore some of the methods of information collection deployed in Sri Lanka and Thailand during the COVID-19 pandemic, and offer policy recommendations for future pandemics.
The fears are that those who are connected or corrupt will get free vaccines, even if they are not on the priority list; or that vaccines obtained for the free channel will be diverted to the pay channel, allowing private providers to make excessive profits which will feed the corruption.
Rohan Samarajiva and Ramathi Bandaranayake presented preliminary findings from our work on risk communication during COVID-19.
Rohan Samarajiva and Ramathi Bandaranayake presented preliminary findings from our work on risk communication during COVID-19.
Chair Rohan Samarajiva was interviewed by Roar Media on the implications of using drones for identifying those violating curfew orders.
Key considerations and recommendations for public health officials in developing wearable contact tracing solutions during COVID-19
This policy brief details guidance on making decisions in a pandemic.
Sometime in March 2018, the Sri Lankan government blocked access to Facebook, citing the spread of hate speech on the platform and tying it to the incidents of mob violence in Digana, Kandy.
Wijeratne, Y., de Silva, N. (2020). Sinhala Language Corpora and Stopwords from a Decade of Sri Lankan Facebook. LIRNEasia.
App-based contact tracing solutions have become popular during COVID-19. However, given their mixed results, wearable technology may prove to be the future.
LIRNEasia’s Data Algorithms and Policy workstream includes research on epidemiology as well as research on the potential uses of satellite imagery for development purposes. Like everyone (it seems) we too are avidly following the massive outpouring of research on COVID-19. Thus, we were intrigued by the recent prepublication from Harvard on when COVID-19 may have arisen in Wuhan. We have been somewhat skeptical about the conclusions that could be drawn from search terms in countries with low Internet use and different cultural attitudes to treatment of disease. But we are intrigued by the reported co-incidence of search terms related to gastro-intestinal and respiratory problems.
A research brief which explores the key data sources, algorithmic techniques and roadblocks in applying remote sensing techniques for development.