A Novel Cascade Model for End-to-End Aspect-Based Social Comment Sentiment Analysis

Abstract

The end-to-end aspect-based social comment sentiment analysis (E2E-ABSA) task aims to discover human’s fine-grained sentimental polarity, which can be refined to determine the attitude in response to an object revealed in a social user’s textual description. The E2E-ABSA problem includes two sub-tasks, i.e., opinion target extraction and target sentiment identification. However, most previous methods always tend to model these two tasks independently, which inevitably hinders the overall practical performance. This paper investigates the critical collaborative signals between these two sub-tasks and thus proposes a novel cascade social comment sentiment analysis model for jointly tackling the E2E-ABSA problem, namely CasNSA. Instead of treating the opinion target extraction and target sentiment identification as discrete procedures in previous works, our new framework takes the contextualized target semantic encoding into consideration to yield better sentimental polarity judgment. Additionally, extensive empirical results show that the proposed approach effectively achieves a 68.13% F1-score on SemEval-2014, 62.34% F1-Score on SemEval-2015, 56.40% F1-Score on SemEval-2016, and 50.05% F1-score on a Twitter dataset, which is higher than the existing approaches. Ablated experiments demonstrate that the CasNSA model substantially outperforms state-of-the-art methods, even when using fixed words embedding rather than pre-trained BERT fine tuning. Moreover, in-depth performance analysis on the social comment datasets further validates that our work gains superior performance and reliability effectively and efficiently in realistic scenarios.

Enhancing Arabic Aspect-Based Sentiment Analysis Using End-to-End Model

“…Additionally, the work involved in ASC relies on the aspect term as a pre-identified feature of the model in conjunction with the input sentence, which is not the case in real-world scenarios. To overcome these limitations, various studies on English ABSA have developed models that can perform these subtasks jointly, either through a hierarchical approach [34] or an End-to-End approach [17,35,36,15]. The following studies correspond to the English E2E-ABSA.…”

“…The GloVe [37] embeddings and targetposition information are used as features. In [17], the authors propose a CasNSA model that consists of several modules: a contextual semantic representation module, a target boundary recognizer, and a sentiment polarity identifier. The model was tested on four different datasets, and the highest F1-score achieved was on the SemEval-2014 dataset.…”

“…F1 score (11) is the harmonic average of Precision and Recall and is used mainly for evaluating sequence labeling tasks [9,13,17,34].…”

“…The aspect boundary labels and the sentiment polarity labels are combined to generate one set of unified labels (Bpositive, I-positive, etc.). Although the unified approach preserves the dependency between the aspect boundaries and their sentiment polarities, it makes model prediction more challenging and can result in performance degradation [17]. The model must identify the aspect boundary and the sentiment polarity without providing any implicit prior information about the aspect terms.…”