Sharing feelings online: studying emotional well-being via automated text analysis of Facebook posts

Abstract

Digital traces of activity on social network sites represent a vast source of ecological data with potential connections with individual behavioral and psychological characteristics. The present study investigates the relationship between user-generated textual content shared on Facebook and emotional well-being. Self-report measures of depression, anxiety, and stress were collected from 201 adult Facebook users from North Italy. Emotion-related textual indicators, including emoticon use, were extracted form users’ Facebook posts via automated text analysis. Correlation analyses revealed that individuals with higher levels of depression, anxiety expressed negative emotions on Facebook more frequently. In addition, use of emoticons expressing positive emotions correlated negatively with stress level. When comparing age groups, younger users reported higher frequency of both emotion-related words and emoticon use in their posts. Also, the relationship between online emotional expression and self-report emotional well-being was generally stronger in the younger group. Overall, findings support the feasibility and validity of studying individual emotional well-being by means of examination of Facebook profiles. Implications for online screening purposes and future research directions are discussed.

Predicting Depression From Language-Based Emotion Dynamics: Longitudinal Analysis of Facebook and Twitter Status Updates (Preprint)

“…Inconsistent with many previous findings [2,3,5,8], the average proportion of positive and negative emotion words used across status updates on both Facebook and Twitter were not associated with depression. Other approaches using the LIWC 2007 positive and negative dictionaries have found that as negative emotion expression increases, so does the ratings of self-reported depression severity (e.g., [5]).…”

“…Studies to date have primarily considered how the relative frequency of words indicating positive and negative emotion relate to other characteristics such as mental health status, or which words (or set of words) best predict different outcomes. Such studies have indicated that the frequent expression of negative emotion words in status updates can accurately identify individuals experiencing symptoms of depression [2][3][4][5]. However, an individual's mental health is likely to be reflected by more than just the average frequency or the type of words used; variability in emotional expression over time might also provide significant insights.…”

“…At a broad level, the frequent expression of negative affect within social media status updates has been associated with higher levels of depression symptoms [2,3,5,[7][8][9][10]. Frequently expressing positive affect, on the other hand, tends to be associated with lower levels of depression and greater levels of well-being [8,11,12].…”

“…Other approaches using the LIWC 2007 positive and negative dictionaries have found that as negative emotion expression increases, so does the ratings of self-reported depression severity (e.g., [5]). This could be due in part to the very small sample used here; language is noisy [41], and with only 29 and 49 participants in the Facebook and Twitter samples respectively, the signal may not be enough to counteract that noise.…”

Applying Natural Language Processing Techniques to an Assessment of Student Conceptual Understanding

“…Now, researchers are moving on to more meta-level analyses. This ranges from the simple frequency tracking of emotion words for the purpose of estimating Facebook user sentiment 19 to automatically assessing the correctness of student responses in a classroom setting using complex machine learning algorithms and artificial intelligence 15 .…”