An Aspect Extraction Framework using Different Embedding Types, Learning Models, and Dependency Structure
This work addresses aspect extraction for fine-grained sentiment analysis, particularly for Turkish language processing, but is incremental as it builds on existing methods with adaptations and new data.
The paper tackled aspect extraction for sentiment analysis by proposing models using diverse embeddings, learning models, and tree positional encoding based on dependency parsing, and introduced a new Turkish dataset via machine translation; experiments on Turkish datasets showed the models mostly outperformed prior studies, with tree positional encoding boosting performance.
Aspect-based sentiment analysis has gained significant attention in recent years due to its ability to provide fine-grained insights for sentiment expressions related to specific features of entities. An important component of aspect-based sentiment analysis is aspect extraction, which involves identifying and extracting aspect terms from text. Effective aspect extraction serves as the foundation for accurate sentiment analysis at the aspect level. In this paper, we propose aspect extraction models that use different types of embeddings for words and part-of-speech tags and that combine several learning models. We also propose tree positional encoding that is based on dependency parsing output to capture better the aspect positions in sentences. In addition, a new aspect extraction dataset is built for Turkish by machine translating an English dataset in a controlled setting. The experiments conducted on two Turkish datasets showed that the proposed models mostly outperform the studies that use the same datasets, and incorporating tree positional encoding increases the performance of the models.