Journal
COMMUNICATION METHODS AND MEASURES
Volume 15, Issue 2, Pages 121-140Publisher
ROUTLEDGE JOURNALS, TAYLOR & FRANCIS LTD
DOI: 10.1080/19312458.2020.1869198
Keywords
Sentiment Analysis; Manual Annotation; Automated Approaches; Measurement; Validity; Evaluation
Categories
Funding
- Nederlandse Organisatie voor Wetenschappelijk Onderzoek [VI.Veni.191R.006]
- Netherlands Organisation for Scientific Research (NWO) [016.145.369]
Ask authors/readers for more resources
Sentiment plays a central role in communication science studies, with this study providing a comprehensive comparison of sentiment analysis methods. The study shows that trained humans or crowd coding still achieve the best performance, with machine learning, especially deep learning, outperforming dictionary-based methods but falling short of human performance. It emphasizes the importance of validating automatic text analysis methods before use and provides a recommended approach for text analysis projects.
Sentiment is central to many studies of communication science, from negativity and polarization in political communication to analyzing product reviews and social media comments in other sub-fields. This study provides an exhaustive comparison of sentiment analysis methods, using a validation set of Dutch economic headlines to compare the performance of manual annotation, crowd coding, numerous dictionaries and machine learning using both traditional and deep learning algorithms. The three main conclusions of this article are that: (1) The best performance is still attained with trained human or crowd coding; (2) None of the used dictionaries come close to acceptable levels of validity; and (3) machine learning, especially deep learning, substantially outperforms dictionary-based methods but falls short of human performance. From these findings, we stress the importance of always validating automatic text analysis methods before usage. Moreover, we provide a recommended step-by-step approach for (automated) text analysis projects to ensure both efficiency and validity.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available