CKG: Improving ABSA with text augmentation using ChatGPT and knowledge-enhanced gated attention graph convolutional networks.

Aspect-level sentiment analysis (ABSA) is a pivotal task within the domain of neurorobotics, contributing to the comprehension of fine-grained textual emotions. Despite the extensive research undertaken on ABSA, the limited availability of training data remains a significant obstacle that hinders the performance of previous studies. Moreover, previous works have predominantly focused on concatenating semantic and syntactic features to predict sentiment polarity, which inadvertently severed the intrinsic connection. Several studies have attempted to utilize multi-layer graph convolution for the purpose of extracting syntactic characteristics. However, this approach has encountered the issue of gradient explosion. This paper investigates the possibilities of leveraging ChatGPT for aspect-level text augmentation. Furthermore, we introduce an improved gated attention mechanism specifically designed for graph convolutional networks to mitigates the problem of gradient explosion. By enriching the features of the dependency graph with a sentiment knowledge base, we strengthen the relationship between aspect words and the polarity of the contextual sentiment. It is worth mentioning that we employ cross-fusion to effectively integrate textual semantic and syntactic features. The experimental results substantiate the superiority of our model over the baseline models in terms of performance.

Executive function and attentional bias as serial mediators in the relationship between frailty and depressive symptoms among older inpatients: A cross-sectional study.

AIMS AND OBJECTIVES: To examine the serial mediating effect of executive function and attentional bias in the relationship between frailty and depressive symptoms. BACKGROUND: Although the role of frailty in predicting depression has been well documented, the underlying mechanisms remain unclear. DESIGN: A cross-sectional study was conducted with 667 older inpatients aged 60-90 years in the internal medicine wards of a hospital in China. METHODS: Attentional bias, frailty and depressive symptoms were assessed using the Attention to Positive and Negative Information Scale, the Physical Frailty Phenotype and the 5-item Geriatric Depression Scale. Executive function was measured using 3 tests, including digital backward, category Verbal Fluency Test and Trail Making Test. The study followed the STROBE guideline. RESULTS: The latent profile analysis (LPA) identified four patterns of attentional bias, namely "no positive bias & no negative bias" (class 1, 9.3%), "minor positive bias & no negative bias" (class 2, 48.0%), "major positive bias & minor negative bias" (class 3, 25.6%) and "major positive bias & no negative bias" (class 4, 17.1%). Regression analysis found that frailty was associated with depressive symptoms. Frailty was also negatively associated with executive function, which was a protective factor for attentional bias class 1, 2 and 3 with reference to class 4. Attentional bias class 1 and 2 but not class 3 was associated with depressive symptoms with reference to class 4. The joint significance test confirmed executive function and attentional bias as serial mediators linking frailty to depressive symptoms. DISCUSSION: Unlike robust older adults who have the age-related positivity effect, frail older adults have attentional bias deficits due to executive dysfunction, and consequently experience clinically relevant depressive symptoms. RELEVANCE TO CLINICAL PRACTICE: Healthcare providers should take executive function training and attentional bias regulation into consideration to reduce the detrimental effects of frailty on emotional well-being.