Search

Aspect-based sentiment analysis has achieved many results in recent years, but most of the research focuses on goods, services, and topics. The research in the medical field is very limited. Considering the problem that the fish disease descriptions contain large numbers of emotional tendencies but the existing data are insufficient in this field, a dataset named Diseases of Fish Animals (DFA) is constructed. In this paper, we propose a feature interaction model based on an adversarial strategy to learn the relationship between aspects and texts by improving the attention mechanism. Aiming at the problem that the fusion effect is reduced due to the difference in feature distribution space during the interaction process, an adversarial strategy is designed to align text and aspect features. Experiments are carried out on the DFA dataset, which involves 7 aspects and 3 sentiment polarity and contains more than 4700 samples. The experimental results show that the accuracy and F1 of the model are 87.07% and 87.19% respectively. Although the model proposed in this paper achieves the best results on DFA, there is still a certain gap for precision medicine diagnosis and further efforts are needed. [ABSTRACT FROM AUTHOR]

Abstract  : In response to the challenges of accurately identifying event triggers and elements in long texts related to aquaculture, existing models struggle to differentiate between elements and triggers, as well as effectively recognize complete entity texts. To tackle this issue, this study proposes an algorithm for extracting fish disease events based on pseudo triggers and augmented event element data. The method starts by constructing pseudo samples using the original dataset. Two types of noise datasets are then generated: a trigger noise dataset constructed based on fish disease triggers and an entity noise dataset with varying levels of entity noise constructed based on fish disease entities. Next, three parallel neural networks are deployed to extract sample features from these datasets. The fish disease event extraction for the source dataset employs multi-label classification. For the trigger noise dataset, the sample features are activated using the sigmoid function, and the MRSE loss is utilized for optimization of this branch. For the entity noise dataset, the sample features are activated using the Relu function, and the XOR loss is used for optimization. Finally, the losses from the three branches are combined with weighted summation to obtain the fusion loss. The experimental results on the fish disease dataset used in this paper show that the proposed algorithm achieves an average accuracy of 78.71%, 78.95%, and 79.43% on F1, recall, and precision, respectively, which is a maximum improvement of 11.201%, 11.849%, and 12.421% in accuracy with respect to the baseline model on F1, recall, and precision, respectively. [ABSTRACT FROM AUTHOR]