Back

Social Listening: A Thematic Analysis of COVID-19 Discussion on Social Media

Afolabi, D. S. A.; Folorunso, S. O.; Bunyula, Z. S.; Banjo, O. O.; Matshika, S. S.; Warrie, W. U.; Ngqambela, N.; Adepoju, A. E.; Rabophala, H.; Abimbola, O. V.; Olanipekun, M. S.; Odukoya, A. L.

2020-07-28 infectious diseases
10.1101/2020.07.25.20162040 medRxiv
Show abstract

COVI-19 is a variant of coronavirus diseases that has destabilised the entire world and whose cure as at mid-2020 has become elusive. Social media is ablaze with discussions around the pandemic. There is the dire need to delineate the on-going conversations on the infection with the intention of creating awareness on peoples reaction, opinion, action and recommendation that are inimical to the wellbeing of the populace. Hence, this study is geared towards performing thematic analysis of the discussions on social media about COVID-19. We programmatically retrieved data from twitter between 1st March, 2020 to 30th June 2020 with covid-19 related keywords. We processed the data and later categorised them into themes that evolved from the tweets namely Herbs and Vegetables as COVID-10 Panacea, Self-Medication Due to Prescription by Non-Medical Practitioners on Social Media, Conspiracy Theories on COVID-19 and Fear and Anxiety Associated with COVID-19. The results show that many are resulting to herbs to protect themselves against the disease; taking drugs without doctors prescription; believing in conspiracy theories and having certain degree of fear.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.