CAMBRIDGE, Mass. — Among all the disagreements between people, cultures, and countries around the world — there is one thing that seems to be universally true: Mondays downright stink. Research shows that for most people, the start of a new week can leave just about anyone in a foul mood. According to a new study however, the COVID-19 pandemic has been almost five times more depressing than the Monday morning blues.
The COVID-19 pandemic’s impact on mental health was worked out from an analysis of hundreds of millions of social media posts by MIT researchers. Worldwide, the first wave induced a reduction in mood 4.7 times as large as going back to work after the traditional weekend break.
The finding is based on 654 million messages on social media networks Twitter and Weibo from 10.56 million individuals across 100 countries. Artificial intelligence made the groundbreaking calculation by examining the language used. It measures for the first time just how demoralizing and stressful COVID-19 has been for people around the world.
“The takeaway here is that the pandemic itself caused a huge emotional toll, four to five times the variation in sentiment observed in a normal week,” says Siqi Zheng, an MIT professor and study co-author-in a statement.
Pandemic blues worse than natural disasters, pollution
The computer neural network showed that the early pandemic months were like a “really, really bad Monday” for social media users globally Typically, people express the most upbeat emotions on weekends and the most negative on Monday.
The study looked at posts published between January 1 and May 31, 2020. Machine learning evaluated content in relation to historical norms There were bigger mood changes than those triggered by natural disasters, extreme weather or the effects of pollution.
“The reaction to the pandemic was also three to four times the change in response to extreme temperatures,” says study co-author Yichun Fan, a PhD candidate at MIT. “The pandemic shock is even larger than the days when there is a hurricane in a region.”
The greatest drops occurred in Australia, Spain, the United Kingdom, and Colombia. Least impacted was Bahrain, Botswana, Greece, Oman, and Tunisia.
Surprisingly, lockdowns did not appear to have much of an effect on public mood.
“You cannot expect lockdowns to have the same effect on every country, and the distribution of responses is quite wide,” says Fan. “But we found the responses actually largely centeredd around a very small positive reaction to lockdowns. It is definitely not the overwhelmingly negative impact on people that might be expected.”
In countries badly hit by COVID, this may reflect that more psychological distress would occur by allowing the virus to propagate without such restrictions.
“On the one hand, lockdown policies might make people feel secure, and not as scared,” explains Zheng. “On the other hand, in a lockdown when you cannot have social activities, it is another emotional stress. The impact of lockdown policies perhaps runs in two directions.”
Some countries took as long as 29 days to erase half the drop off in mood. Almost a fifth (18%) did not recover to pre-pandemic levels.
The study demonstrates how data from social media can help us understand changes in emotion on a global scale. But social media users are not representative of the wider population. The method is a useful tool alongside surveys.
“The traditional approach is to use surveys to measure wellbeing or happiness,” adds Zheng. “But a survey has smaller sample size and low frequency. This a real time measure of people’s sentiment.”
South West News Service writer Mark Waghorn contributed to this report.