The results below are likely only meaningful to subject matter experts because the source dataset employs abbreviations, jargon and/or otherwise non-obvious labels. You may get in touch
to help improve the source data, or you may browse Analyst-2
to find more accessible datasets.
SentiWS is a publicly available German-language resource for sentiment analysis
SentimentWortschatz, or SentiWS for short, is a publicly available German-language resource for sentiment analysis, opinion mining etc. It lists positive and negative polarity bearing words weighted within the interval of [-1; 1] plus their part of speech tag, and if applicable, their inflections. It not only contains adjectives and adverbs explicitly expressing a sentiment, but also nouns and verbs implicitly containing one.
SentiWS is licensed under a Creative Commons Attribution-Noncommercial-Share Alike 3.0 Unported License.
If you use SentiWS in your work it is kindly asked you to cite their paper as
R. Remus, U. Quasthoff & G. Heyer: SentiWS - a Publicly Available German-language Resource for Sentiment Analysis.
In: Proceedings of the 7th International Language Resources and Evaluation (LREC'10), pp. 1168-1171, 2010
Update 2021/08/05 (older version - v1.8c, but with different structure):
SentiWS as published by the University of Leipzig is poorly structured for an automatic evaluation. To make work easier, Marco Lehner made new structured files ("SentiWS_ML_positiv" and "SentiWS_ML_negativ") which he also published on his website: http://marco-lehner.de/2017/04/10/Sentimentanalyse_mit_SentiWS_in_R.html. He used version v1.8c.
Like SentiWS, the files are also available under a Creative Commons Attribution-Noncommercial-Share Alike 3.0 Unported License.
From these files I extracted the positive resp. negative words and saved it as txt files ("positive-words.txt" / "negative-words.txt").
- Table ‘SentiWS ML negativ’ consists of 15,632 data rows along three dimensions: ‘Column #1’, ‘Wort’ and ‘sentiment score’
- Table ‘SentiWS ML positiv’ consists of 15,649 data rows along three dimensions: ‘Column #1’, ‘V1’ and ‘V2’
- Table ‘SentiWS v2.0 Negative’ consists of 1826 data rows along three dimensions: ‘Abbau|NN’, ‘-0.058’ and ‘Abbaus,Abbaues,Abbauen,Abbaue,Abbauten’
- Table ‘SentiWS v2.0 Positive’ consists of 1643 data rows along three dimensions: ‘Abmachung|NN’, ‘0.0040’ and ‘Abmachungen’