Skip to main content
SpringerLink
Log in

Sentiment Analysis for German Facebook Pages

  • Conference paper
  • First Online:
Natural Language Processing and Information Systems (NLDB 2016)

Part of the book series: Lecture Notes in Computer Science ((LNISA,volume 9612))

Abstract

Social media monitoring has become an important means for business analytics and trend detection, for instance, analyzing the sentiment towards a certain product or decision. While a lot of work has been dedicated to analyze sentiment for English texts, much less effort has been put into providing accurate sentiment classification for the German language. In this paper, we analyze three established classifiers for the German language with respect to Facebook posts. We then present our own hierarchical approach to classify sentiment and evaluate it using a data set of \(\sim \)640 Facebook posts from corporate as well as governmental Facebook pages. We compare our approach to three sentiment classifiers for German, i.e. AlchemyAPI, Semantria and SentiStrength. With an accuracy of 70 %, our approach performs better than the other classifiers. In an application scenario, we demonstrate our classifier’s ability to monitor changes in sentiment with respect to the refugee crisis.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    http://blog.wishpond.com/post/115675435109/40-up-to-date-facebook-facts-and-stats.

  2. 2.

    http://scikit-learn.org/.

  3. 3.

    http://www.nltk.org/.

  4. 4.

    http://snowball.tartarus.org/.

  5. 5.

    Classifiers such as Naive Bayes and Logistic Regression did not yield better results.

  6. 6.

    Experiments with a single layer classifier (same settings) led to an accuracy of 0.68 %.

  7. 7.

    The application can be downloaded from the project GitHub repostory https://github.com/fsteinbauer/nldb16-sentiment-analysis.

References

  1. He, W., Zha, S., Li, L.: Social media competitive analysis and text mining: a case study in the pizza industry. J. Inf. Manag. 33(3), 464 (2013)

    Article  Google Scholar 

  2. Kasper, W., Vela, M.: Sentiment analysis for hotel reviews. In: Proceedings of the Computational Linguistics-Applications Conference (2011)

    Google Scholar 

  3. Meehan, K., Lunney, T., Curran, K., McCaughey, A.: Context-aware intelligent recommendation system for tourism. In: IEEE International Conference on Pervasive Computing and Communications Workshops (2013)

    Google Scholar 

  4. Momtazi, S.: Fine-grained German sentiment analysis on social media. In: Proceedings of the 8th Conference on Language Resources and Evaluation (2012)

    Google Scholar 

  5. Neri, F., Aliprandi, C., Capeci, F., Cuadros, M., By, T.: Sentiment analysis on social media. In: Advances in Social Networks Analysis and Mining (2012)

    Google Scholar 

  6. Ortigosa, A., Martín, J.M., Carro, R.M.: Sentiment analysis in facebook and its application to e-learning. Comput. Human Behav. 31, 527 (2014)

    Article  Google Scholar 

  7. Thelwall, M., Buckley, K., Paltoglou, G., Cai, D., Kappas, A.: Sentiment in short strength detection informal text. J. Am. Soc. Inf. Sci. Technol. 61(12), 2544 (2010)

    Article  Google Scholar 

  8. Troussas, C., Virvou, M., Espinosa, K., Llaguno, K., Caro, J.: 4th International Conference on Information, Intelligence, Systems and Applications (2013)

    Google Scholar 

  9. Wiebe, J., Wilson, T.: Learning to disambiguate potentially subjective expressions. In: Proceedings of the 6th Conference on Natural Language Learning (2002)

    Google Scholar 

Download references

Acknowledgements

This work is funded by the KIRAS program of the Austrian Research Promotion Agency (FFG) (project nr. 840824). The Know-Center is funded within the Austrian COMET Program under the auspices of the Austrian Ministry of Transport, Innovation and Technology, the Austrian Ministry of Economics and Labour and by the State of Styria. COMET is managed by the Austrian Research Promotion Agency FFG.

Author information

Authors and Affiliations

  1. University of Technology, Graz, Austria

    Florian Steinbauer

  2. Know-Center GmbH Graz, Graz, Austria

    Mark Kröll

Authors
  1. Florian Steinbauer
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mark Kröll
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mark Kröll .

Editor information

Editors and Affiliations

  1. ConservatoireNational desArts et Métiers, Paris, France

    Elisabeth Métais

  2. University of Salford, Salford, United Kingdom

    Farid Meziane

  3. University of Salford, Salford, United Kingdom

    Mohamad Saraee

  4. Oakland University, Rochester, Michigan, USA

    Vijayan Sugumaran

  5. University of Salford, Salford, United Kingdom

    Sunil Vadera

Rights and permissions

Reprints and permissions

Copyright information

© 2016 Springer International Publishing Switzerland

About this paper

Cite this paper

Steinbauer, F., Kröll, M. (2016). Sentiment Analysis for German Facebook Pages. In: Métais, E., Meziane, F., Saraee, M., Sugumaran, V., Vadera, S. (eds) Natural Language Processing and Information Systems. NLDB 2016. Lecture Notes in Computer Science(), vol 9612. Springer, Cham. https://doi.org/10.1007/978-3-319-41754-7_44

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-41754-7_44

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-41753-0

  • Online ISBN: 978-3-319-41754-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation