Investigating the affective part of subjective well-being (SWB) by means of sentiment analysis

ABSTRACT

The use of multiple measures for the operationalization of subjective well-being (SWB) is highly recommended, as each approach brings exposure to different errors. To supplement the approaches proposed in the literature, the paper at hand outlines a complemental text mining technique – sentiment detection – which presents an efficient solution for big data analyses. Empirical findings from its application to 466 semi-structured life satisfaction (LS) interviews are contrasted with happiness and satisfaction ratings derived from the interviewees themselves as well as from external raters. In addition, detailed insights are presented into the use of emotive language in LS interviews and into relations between base emotions for the following affective features: anger, joy, sadness, disgust, surprise, trust, fear, and anticipation.

KEYWORDS:

• Subjective well-being
• mixed methods
• text mining
• sentiment analysis
• verbal emotion recognition

Disclosure statement

No potential conflict of interest was reported by the author.

Supplementary material

Supplemental data for this article can be accessed here.

Additional information

Funding

This work was supported by the Anniversary Fund of the Austrian National Bank under Grant 14399 (https://www.oenb.at/jublfonds/jublfonds/projectsearch?id=5289&action=detailview&origin=resultlist).

Notes on contributors

C. Weismayer

Christian Weismayer studied Business Economics at the Vienna University of Economics and Business (WU) and Technical Mathematics at the Leopold-Franzens University of Innsbruck. He holds a doctoral degree in social and economic sciences and was working at WU as a research associate from 2006 to 2011. Between 2011 and 2017 he was part of the Department of Applied Statistics and Economics, since 2017, he joins the Department of Sustainability, Governance, and Methods (SGM), both at Modul University Vienna. He participated in several projects, funded by the Anniversary Fund of the Austrian National Bank (OeNB), the Anniversary Fund of the City of Vienna, the Austrian Research Promotion Agency (FFG), Eurostat, ESPON – EGTC (European Observation Network for Territorial Development and Cohesion – European Grouping on Territorial Cooperation) and collaborations with Statistics Austria. His research interests lie in the application and development of data mining techniques.