Before using the service, please read the preliminary information containing a description of steps that enable access to the CLARIN-PL developer interface.
A service for aspect-based sentiment analysis. It categorizes data by aspects and identifies the sentiment assigned to each aspect.
It is based on the Aspect-Based Sentiment Analysis (ABSA) technique which consists in dividing the input data by aspect into tokens equal to words and identifying the emotional valence assigned to them.
Selection of the language of the input data.
AspectEmo can be run:
lang - selection of the language of the analyzed text, possible values:
pl - defaulten - EnglishThe service can be run in the Windows system with default values using the following LPMN query: ['any2txt','aspectemo']
[['any2txt','aspectemo']] - input data in the form of a compressed directory (.zip)['any2txt',{'aspectemo':{'lang':'en'}}] - input data in EnglishA text file.
JSON file containing the following information:
tokens - the extracted tokenslabels - labels identifying the emotional character assigned to the tokens according to the 7 possible classes:
a_minus_m - strongly negativea_minus_s - slightly negativea_zero - neutrala_plus_s - slightly positivea_plus_m - strongly positivea_amb - ambiguousIn Colab: AspectEmo - Determining the emotional character of words
Joanna Szołomicka, Jan Kocon (2022) "MultiAspectEmo: Multilingual and Language-Agnostic Aspect-Based Sentiment Analysis", 2022 IEEE International Conference on Data Mining Workshops (ICDMW), Orlando, USA, 443-450.
Jan Kocoń, Jarema Radom, Ewa Kaczmarz-Wawryk, Kamil Wabnic, Ada Zajączkowska, Monika Zaśko-Zielińska (2021) "AspectEmo: Multi-Domain Corpus of Consumer Reviews for Aspect-Based Sentiment Analysis", 2021 International Conference on Data Mining Workshops (ICDMW), Auckland, New Zealand, 166-173.
(C) CLARIN-PL