No abstract

This survey focuses on deep learning-based aspect-level sentiment classification (ASC), which aims to decide the sentiment polarity for an aspect mentioned within the document. Along with the success of applying deep learning in many applications, deep learning-based ASC has attracted a lot of interest from both academia and industry in recent years. However, there still lack a systematic taxonomy of existing approaches and comparison of their performance, which are the gaps that our survey aims to fill. Furthermore, to quantitatively evaluate the performance of various approaches, the standardization of the evaluation methodology and shared datasets is necessary. In this paper, an in-depth overview of the current state-of-the-art deep learning-based methods is given, showing the tremendous progress that has already been made in ASC. In particular, first, a comprehensive review of recent research efforts on deep learningbased ASC is provided. More concretely, we design a taxonomy of deep learning-based ASC and provide a comprehensive summary of the state-of-the-art methods. Then, we collect all benchmark ASC datasets for researchers to study and conduct extensive experiments over five public standard datasets with various commonly used evaluation measures. Finally, we discuss some of the most challenging open problems and point out promising future research directions in this field. INDEX TERMS Aspect based sentiment analysis, aspect-level sentiment classification, attention, convolutional neural network (CNN), deep learning, memory network, neural networks, recurrent neural network (RNN).

No abstract

The aim of this study was to determine whether the serum level of irisin can be a candidate to predict the spinal metastasis in patients with breast cancer.In a cross-sectional study, 148 patients were recruited. Of those, 53 (35.8%) had spinal metastasis. The baseline characteristics were compared by status of spinal metastasis. Multiple logistic regression analysis was used to determine whether the serum irisin can be a candidate for predicting breast cancer to spinal metastasis. The correlation coefficient analysis was used to confirm the correlation between the serum irisin and lipid metabolic parameters and body mass index (BMI), respectively.The serum irisin was higher in patients without spinal metastasis (7.60 ± 3.80). Multivariable analysis showed that the serum irisin was protective to the presence of spinal metastasis in patients with breast cancer after adjustments of age and BMI (odds ratio, 0.873; 95% confidence interval, 0.764–0.999). Furthermore, there was a positive correlation between the serum irisin and BMI (r = 0.263). The patients with metabolisc syndrome (MetS) had a higher level in serum irisin. In addition, the higher numbers of MetS components were associated with higher serum irisin.Higher serum irisin can be a protective factor of spinal metastasis in patients with breast cancer. The BMI is positively associated with the serum level of irisin. Furthermore, patients with MetS tended to have a higher level of serum irisin.