Natural language sentiment as an indicator of depression and anxiety symptoms: a longitudinal mixed methods study¹

ABSTRACT

The study tested how the use of positive- (e.g. beautiful) and negative-valenced (e.g. horrible) words in natural language and its change in time affects the severity of depression and anxiety symptoms among depressed and non-depressed individuals. This longitudinal mixed methods study (N = 40 participants, n = 1440 narratives) with three measurements within a year showed that at the between-person level the use of negative-valenced words was strongly associated with the increase in anxiety and depression symptoms over time while the use of positive-valenced words was slightly associated with the decrease in anxiety and depression symptom. These effects were not supported for within-person level (i.e. changes in word usage). No significant differences were observed in the effects between depressed and non-depressed groups. Summing up, the overall use of positive- and negative-valenced words (particularly negative-valenced words) had a stronger effect on the severity of psychopathological symptoms than their change over time. The results were discussed in the context of natural language processing and its application in diagnosing depression and anxiety symptoms.

KEYWORDS:

• Depression
• anxiety
• language
• valence
• word sentiment

Disclosure statement

The research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Data deposition

The data for this study can be found on the Open Science Foundation https://osf.io/zvmqx/?view_only = bfe1b6428bfe4bb8ae0f25237b8ba4ce.

Ethical statement

The project was approved by the Academic Human Research Ethics Committee (159-2017/2018 and 183-2018-2019).

Informed consent

Interested volunteers were informed about the nature and purpose of the study and offered the opportunity to participate. When they chose to participate, they were informed that they could discontinue at any time and their responses would be confidential and not revealed to anyone.

Code availability

All analyses were done in R (v4.2.0). Data and R syntax are available online (https://osf.io/zvmqx/?view_only = bfe1b6428bfe4bb8ae0f25237b8ba4ce).

Author contributions

Table

Additional information

Funding

This work was supported by the following grants: Narodowe Centrum Nauki [grant number 2017/01/X/HS6/02022]; Maria Grzegorzewska University [grant number BNS 52/20-P].