No abstract

Word embeddings that can capture semantic and syntactic information from contexts have been extensively used for various natural language processing tasks. However, existing methods for learning contextbased word embeddings typically fail to capture sufficient sentiment information. This may result in words with similar vector representations having an opposite sentiment polarity (e.g., good and bad), thus degrading sentiment analysis performance. Therefore, this study proposes a word vector refinement model that can be applied to any pre-trained word vectors (e.g., Word2vec and GloVe). The refinement model is based on adjusting the vector representations of words such that they can be closer to both semantically and sentimentally similar words and further away from sentimentally dissimilar words. Experimental results show that the proposed method can improve conventional word embeddings and outperform previously proposed sentiment embeddings for both binary and fine-grained classification on Stanford Sentiment Treebank (SST).

No abstract

The process of rural-to-urban migration in China is accelerating with increased modernization and industrialization. To address the issues of health outcomes and geographic mobility among this population, data from 4,208 rural-to-urban migrants in two major metropolitans of China were analyzed. Results indicate that average duration of migration was 4.3 years, with younger migrants being more mobile than their older counterparts. After controlling for possible confounders, increases in mobility were associated with unstable living arrangements, substandard employment conditions, suboptimal health status, inferior health-seeking behaviour, elevated level of substance use, depressive symptoms and expression of dissatisfaction with life and work. The findings in the present study underscore the need for improved living and employment conditions and increased healthcare services available to rural-to-urban migratory population.

MicroRNAs (miRNAs) play important roles as significant biomarkers in disease diagnostics. Here, an electrochemical biosensor was developed for the quick, sensitive, and specific detection of miRNAs from humanserum samples using three-dimensional (3D) DNA tetrahedron-structured probes (TSPs) and duplex-specific nuclease (DSN). The designed TSPs were composed of a recognition sequence that corresponded to a target miRNA and a Gquadruplex sequence that was combined with hemin to mimic the biocatalytic functions for H 2 O 2 reduction and L-cysteine oxidation. After hybridization with miRNA, the TSPs were immobilized on the Au electrode to shape the DNA−RNA double strands, which could be discriminated by DSN for hydrolysis of the DNA in the heteroduplexes to generate significant change in the reduction currents. Under optimal conditions, the biosensor showed a wide linear response ranging from 0.1 fM to 0.1 pM, with a low detection limit of 0.04 fM. Meanwhile, the method showed acceptable accuracy and precision for the determination of miRNAs in serum after a series of assessments.