LT-ABSA

LT-ABSA: Aspect-based Sentiment Analysis

LT-ABSA is an extensible framework for text classification. It is tuned for short-text analysis, e.g. Social Media, individual sentences.

It offers text-wide classification, e.g. polarity identification, as well as identifiaction of individual targets in the text.

LT-ABSA was built for GermEval 2017 Shared Task on Aspect-based Sentiment Analyis, where it did not take part as an "organizers system". But the evaluation shows strong peformance overall.

The software and documentation can be obtained from the GitHub page: LT-ABSA

Demo

Try the API at : http://ltmaggie.informatik.uni-hamburg.de/absa/

How to cite

Ruppert E., Kumar A., Biemann C. (2017): LT-ABSA: An extensible open-source system for document-level and aspect-based sentiment analysis. In Proceedings of the GSCL GermEval Shared Task on Aspect-based Sentiment in Social Media Customer Feedback, pages 55–60, Berlin, Germany. (pdf)

License

LT-ABSA is provided as open source under the Apache License v2.0.