This paper describes our submission to the tasks on Sentiment Analysis of ATE\_ABSITA (Aspect Term Extraction and Aspect-Based Sentiment Analysis). In particular, we focused on Task 3 using an approach based on combining frequency of words with lexicon-based polarities and uses Boosted Trees to predict the sentiment score. This approach achieved a competitive error and, thanks to the interpretability of the building blocks, allows us to show the what elements are considered when making the prediction. We also joined Task 1 proposing a hybrid model that joins rule-based and machine learning methodologies in order to combine the advantages of both. The model proposed for Task 1 is only preliminary.
Questo articolo descrive la nostra sottomissione ai tasks sulla Sentiment Analysis ATE\_ABSITA (Aspect Term Extraction and Aspect-Based Sentiment Analysis). I nostri sforzi si sono concentrati sul Task 3 per il quale abbiamo adottato gli alberi di predizione (Boosted Trees) utilizzando come features di ingresso una combinazione basata sulla frequenza delle parole con la polarità derivate da un lessico. L'approccio raggiunge un errore competitivo e, grazie all'interpretabilità dei moduli intermedi, ci consente di analizzare in dettaglio gli elementi che caratterizzano maggiormente la fase di predizione. Una proposta è stata realizzata anche per il Task 1, dove abbiamo sviluppato un modello ibrido che combina un approcio basato su regole con tecniche Machine Learning. Il modello sviluppato per il Task 1 è solo in fase preliminare.
SentNA@ATE_ABSITA: Sentiment Analysis of Customer Reviews Using Boosted Trees with Lexical and Lexicon-based Features
Mele, FrancescoCo-primo
;Sorgente, Antonio
Co-primo
;Vettigli, GiuseppeCo-primo
2020
Abstract
This paper describes our submission to the tasks on Sentiment Analysis of ATE\_ABSITA (Aspect Term Extraction and Aspect-Based Sentiment Analysis). In particular, we focused on Task 3 using an approach based on combining frequency of words with lexicon-based polarities and uses Boosted Trees to predict the sentiment score. This approach achieved a competitive error and, thanks to the interpretability of the building blocks, allows us to show the what elements are considered when making the prediction. We also joined Task 1 proposing a hybrid model that joins rule-based and machine learning methodologies in order to combine the advantages of both. The model proposed for Task 1 is only preliminary.| File | Dimensione | Formato | |
|---|---|---|---|
|
prod_448625-doc_161697.pdf
accesso aperto
Descrizione: SentNA @ ATE ABSITA: Sentiment analysis of customer reviews using boosted trees with lexical and lexicon-based features
Tipologia:
Versione Editoriale (PDF)
Licenza:
Creative commons
Dimensione
251.54 kB
Formato
Adobe PDF
|
251.54 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.


