Lihui Shi

The goal of aspect-based sentiment analysis (ABSA) is to identify the sentiment polarity of specific aspects in a context. Recently, graph neural networks have employed dependent tree syntactic information to assess the link between aspects and contextual words; nevertheless, most of this research has neglected phrases that are insensitive to syntactic analysis and the effect between various aspects in a sentence. In this paper, we propose a dual-channel edge-featured graph attention networks model (AS-EGAT), which builds an aspect syntactic graph by enhancing the contextual syntactic dependency representation of key aspect words and the mutual affective relationship between various aspects in the context and builds a semantic graph through the self-attention mechanism. We use the edge features as a significant factor to determine the weight coefficient of the attention mechanism to efficiently mine the edge features of the graph attention networks model (GAT). As a result, the model can connect important sentiment features of related aspects when dealing with aspects that lack obvious sentiment expressions, pay close attention to important word aspects when dealing with multiple-word aspects, and extract sentiment features from sentences that are not sensitive to syntactic dependency trees by looking at semantic features. Experimental results show that our proposed AS-EGAT model is superior to the current state-of-the-art baselines. Compared with the baseline models of LAP14, REST15, REST16, MAMS, T-shirt, and Television datasets, the accuracy of our AS-EGAT model increased by 0.76%, 0.29%, 0.05%, 0.15%, 0.22%, and 0.38%, respectively. The macro-f1 score increased by 1.16%, 1.16%, 1.23%, 0.37%, 0.53%, and 1.93% respectively.

In online social networks, finding high-influence nodes is a crucial component of complex network research. A new book impact evaluation method based on user rating is proposed in this research for the social network created by the buying and selling behaviors on the e-commerce platform. It intends to rank the book nodes in accordance with customer feedback data following user purchases. The method calculates the influence score of a book by predicting its popularity based on user evaluations of the book. To verify the validity and accuracy of the method, the research analyzes a real review dataset from Amazon, a large e-commerce platform, and designs two comparison experiments with different time spans and compares them with five other web analytics metrics. The experimental findings show that the method is efficient and precise in evaluating the influence of book nodes.

Background: Chromosome 1q21 aberrations have not been implemented into the routine clinical test yet, and their effect in multiple myeloma is still under investigation. Heterogeneity exists among patients presenting 1q21 gains, e.g., variation in the copy numbers and the size of clone carrying 1q21 gains. The prognostic value of copy number variation and percentage of plasma cells involved remained unclear. Materials and Methods: In the present study, we analyzed the prognostic value of 1q21 in a in a series of 290 cases of newly diagnosed multiple myeloma treated in a prospective, nonrandomized clinical trial (BDH 2008/02). Results: The incidence of patients carrying at least three copies of 1q21 was significantly higher in relapsed MM than in newly diagnosed MM (73 out of 107 [68.2%] vs. 142 out of 290 [48.9%], p=0.001). Among the whole cohort, 278 newly diagnosed MM and 102 relapsed MM had copy number variation information. No statistical difference in the frequency of three, four, or at least five copies copies of 1q21 was found between relapsed and initially diagnosed cases. 1q21 gains showed a profoundly negative impact on survival in patients receiving bortezomib treatment. Patients with 1q21 gains had a significantly shortened PFS (13.5 months vs. 43.0 months, p<0.001) and OS (24.0 months vs. 54.0 months, p50%, which were seen respectively in 28/290 (9.7%) and 114/290 (43.8%) patients with newly diagnosed MM. The median PFS was 6.0 months (95% CI: 1.00-21.5) and 13.5 months (95% CI: 8.87-18.14) respectively, and median OS was 6.0 months (95% CI: 1.00-21.49) and 24.0 months (95% CI: 18.94-29.05) respectively. The difference in PFS and OS were not statistically significant between the two groups (p=0.753 and 0.273 respectively;). No statistically significant differences were found in patients harboring 1q21 gains between bortezomib-based and thalidomide-based chemotherapy groups, and the median PFS and OS in patients receiving bortezomib-based regimens were 13.5 months (vs. 20.0 months; p=0.176) and 24.0 months (vs. 21.0 months; p=0.773) respectively. Therefore, bortezomib was unable to overcome the negative impact of 1q21 gains on survival, and to significantly improve the survival of these patients. Conclusion: Our data demonstrated that copy numbers of 1q21 increased with progression of myeloma and predicted a poor prognosis in MM patients treated with bortezomib-based therapy. Our results also indicate that three copies of 1q21 gains and 20% of plasma cells with this abnormality were enough to confer bortezomib resistance. Chromosome 1q21 gains should be considered a high-risk feature in MM, and 1q21 analysis should be added to the diagnostic panel of FISH probes used in routine assessment of prognosis in patients with MM, especially those receiving bortezomib-based regimens. Disclosures: No relevant conflicts of interest to declare.