README.md

Natural Language Processing (NLP) using Topic Modeling

Application of topic model with special focus on German texts.

Datasets:

• German Political Speeches
• TODO Offenes Parlament
• TODO Project Gutenberg
• TODO German news articles
• TODO German Wikipedia articles

Algorithms:

• TODO LSI - Latent Semantic Indexing (SVD)
• LDA - Latent Dirichlet Allocation
• TODO NMF - Non-negative Matrix Factorization

Tools:

• Gensim
• Mallet
• TODO lda
• TODO NLTK
• TODO sklearn
• TODO BigARTM
• TODO Vowpal Wabbit (Online LDA)
• TODO tmtoolkit
• TODO tcma

Useful and inspirational resources

Topic Modeling Tutorials

About: Building, Evaluating, Visualizing Topic Models

• Gensim Tutorials
  • Topics and Transformations
  • Tutorial on Mallet in Python (2014-03-20)
• Mallet
• pyLDAvis Library
  • http://nbviewer.jupyter.org/github/bmabey/pyLDAvis/blob/master/notebooks/pyLDAvis_overview.ipynb
• Machine Learning Plus Tutorials (Topic Modeling, NLP)
  • Topic modeling visualization – How to present the results of LDA models? (2018-12-04)
  • LDA in Python – How to grid search best topic models? (2018-04-04)
  • Topic Modeling with Gensim (2018-03-26)
  • Lemmatization Approaches with Examples in Python (2018-10-02)
  • Gensim Tutorial
• Data Science Plus Tutorials
  • Topic Modeling in Python with NLTK and Gensim (2018-04-26)
  • Evaluation of Topic Modeling: Topic Coherence (2018-05-03)
• Towards Data Science
  • The complete guide for topics extraction with LDA (Latent Dirichlet Allocation) in Python (2018-12-14)
• WZB Data Science Blog (NLP)
  • Topic Modeling – Background, Hyperparameters and Common pitfalls (2018-01-26)
  • Practical Topic Modeling: Preparation, Evaluation, Visualization (2018-05-17)
  • Topic Model Evaluation in Python with tmtoolkit (2017-11-09)
  • A topic model for the debates of the 18th German Bundestag

Topic Models applied on Wikipedia

• https://radimrehurek.com/gensim/wiki.html
• https://www.kdnuggets.com/2017/11/building-wikipedia-text-corpus-nlp.html

Other NLP

• https://github.com/adbar/German-NLP

Research

• Abteilung Automatische Sprachverarbeitung, Universität Leipzig
  • Leipzig Corpus Miner

Data Sources

• Link List - Wissenschaftszentrum Berlin für Sozialforschung
• Link List - Institut für deutsche Sprache und Linguistik (HU Berlin)
• POLLUX - Informationsdienst Politikwissenschaft
• German Microdata Lab (gesis)
• Leipzig Corpora Collection
• DWDS Corpora

Bibliography

LDA

• David M. Blei, Andrew Y. Ng, Michael I. Jordan. Latent Dirichlet Allocation. In: Journal of Machine Learning Research, 2003

Sentiment

• R. Remus, U. Quasthoff & G. Heyer: SentiWS - a Publicly Available German-language Resource for Sentiment Analysis. In: Proceedings of the 7th International Language Ressources and Evaluation (LREC'10), pp. 1168-1171, 2010