Python package ALDONAr: A Hybrid Solution for Sentence-Level Aspect Based Sentiment Analysis using a Lexicalized Domain Ontology and a Regularized Neural Attention Model. Aspect-based sentiment analysis allows one to compute the sentiment for an aspect in a certain context. One problem in this analysis is that words possibly carry different sentiments for different aspects. Moreover, an aspect’s sentiment might be highly influenced by the domain-specific knowledge. In order to tackle these issues, in this paper, we propose a hybrid solution for sentence-level aspect-based sentiment analysis using A Lexicalized Domain Ontology and a Regularized Neural Attention model (ALDONAr). The bidirectional context attention mechanism is introduced to measure the influence of each word in a given sentence on an aspect’s sentiment value. The classification module is designed to handle the complex structure of a sentence. The manually created lexicalized domain ontology is integrated to utilize the field-specific knowledge. Compared to the existing ALDONA model, ALDONAr uses BERT word embeddings, regularization, the Adam optimizer, and different model initialization. Moreover, its classification module is enhanced with two 1D CNN layers providing superior results on standard datasets.
Keywords for this software
References in zbMATH (referenced in 2 articles )
Showing results 1 to 2 of 2.
- Salim Sazzed; Sampath Jayarathna: SSentiA: A Self-supervised Sentiment Analyzer for classification from unlabeled data (2021) not zbMATH
- Su, Jinsong; Tang, Jialong; Jiang, Hui; Lu, Ziyao; Ge, Yubin; Song, Linfeng; Xiong, Deyi; Sun, Le; Luo, Jiebo: Enhanced aspect-based sentiment analysis models with progressive self-supervised attention learning (2021)