The Emotional Climate of Academia: Exploring Social Media Data as an Indicator of Well-being

Understanding and promoting researchers' well-being is crucial for successful researchoutcomes and a thriving scientific community. Traditional well-being assessments can beresource-intensive, but prior research suggests that sentiment analysis of social media textdata can provide insights into the emotional well-being in the general population. In thisproof-of-concept study, we explore whether social media sentiment can serve as an indicatorof researchers’ well-being on a group-level. Specifically, we analyze the emotional climate ofthe academic community by applying sentiment analysis to a dataset of more than 3.48Million messages from 14,876 psychology researchers, posted on the platform Twitter/Xbetween 2019 and 2021. As this period is one year before and after the onset of thecoronavirus pandemic, we used the findings from COVID-19 research to derive twohypotheses: lower well-being during the pandemic is reflected in more positive/less negativesentiment in researchers’ social media posts (H1), and a stronger impact on femaleresearchers is reflected in even more positive/less negative sentiment in female researchers’posts (H2). Using structural break analysis, the impact of the pandemic was found to bestatistically significant for positive sentiments. A differential effect by gender was observeddescriptively, but did not reach statistical significance. The results suggest a positivity bias inscholarly communication on Twitter/X, with only changes in positive sentiments as anindicator of researchers’ emotional well-being. Gender differences were found for generalsentiment magnitude, but not in the effect of the pandemic. Exploratory analysis of cognitivewell-being revealed relationships and accomplishment as the predominant PERMA+4dimensions in researchers' posts. We discuss promising expansions of our approach andhighlight practical implications for policymakers.