Emotion cause extraction is one of the most important applications in natural language processing tasks. It a difficult challenge due to complex semantic information between emotion description and whole document. Previous approaches have revealed that clause an indicator emotion-cause extraction. As such, selecting suitable has become interesting challenge. Different from existed selection methods which mainly focus on similarity description, this paper, we proposed hierarchical...

Community-based Question Answering (CQA) has become popular in knowledge sharing sites since it allows users to get answers complex, detailed, and personal questions directly from other users. Large archives of historical associated have been accumulated. Retrieving relevant that best match a question is an essential component CQA service. Most state the art approaches are based on bag-of-words models, which proven successful range text matching tasks, but insufficient for capturing...

Recommender systems, which analyze users' preference patterns to suggest potential targets, are indispensable in today's society. Collaborative Filtering (CF) is the most popular recommendation model. Specifically, Graph Neural Network (GNN) has become a new state-of-the-art for CF. In GNN-based recommender system, message dropout usually used alleviate selection bias user-item bipartite graph. However, might deteriorate system's performance due randomness of dropping out outgoing messages...

The technology acceptance model (TAM) has been regarded as a promising for understanding adoption and can be extended to different situations. Currently, mobile payment services have widely applied in people’s daily lives China, their critical success factors is becoming important. Mobile payments are complex system, large number of affect success. Since directly related financial issues, wide relies heavily on trust. We developed based the TAM investigate most influential building trust...

WeChat payment has recently become a popular mobile service in China by bundling with WeChat, the most social network China. It is interesting to investigate reasons for its popularity. In this research, we applied technology acceptance model predict acceptability and identify variables attributing addition primary explanatory variables, i.e., Perceived Ease of Use Usefulness, proposed framework further extended include constructs Social Interaction, Trust, Enjoyment Context. The results...

Sentiment Classification of web reviews or comments is an important and challenging task in Web Mining Data due to the increasing social media e-commerce industry. This paper presents a novel approach using association rules for sentim

Sentiment analysis is one of the most important challenges to understand opinions online. In this research, inspired by idea that structural information among words, phrases and sentences playing role in identifying overall statement's polarity, a novel sentiment model proposed based on recurrent neural network. The key point approach, order utilise character, take partial document as input then next parts predict label distribution rather than word. method learns words representation...

With the rapid development of Internet technology and social media, people are accustomed to making comments on Internet. Sentiment analysis, as an efficient technique, has been used by researchers in tasks analysing sentiment polarity under these comments. To better achieve this target, fundamental challenge is how extract feature build a proper mechanism learn them. A lot word embedding based deep learning models for analysis proposed literature. And semi-supervised methods make it...

We analyze the defects of window-based TCP algorithm in datacenter networks and propose Rate-based Datacenter (RDT) this paper. The RDT combines rate-based congestion control technology with ECN (Explicit Congestion Notification) mechanism DCTCP. experiments NS2 show that has a potential to completely avoid incast collapse datacenters inherit low latency advantages

During the process of building business agility, concept Service Oriented Architecture (SOA) is proposed and widely lauded as an innovative oriented solution. One most fundamental components in SOA based applications a service, which represents repeatable functionalities to help development loosely coupled applications. Due its important role implementing for achieving dynamic process, how build scalable, reliable service efficiently has become vital challenge, while lifecycle management...

Collaborative filtering (CF) is an essential technique in recommender systems that provides personalized recommendations by only leveraging user-item interactions. However, most CF methods represent users and items as fixed points the latent space, lacking ability to capture uncertainty. In this paper, we propose a novel approach, called Wasserstein dependent Graph ATtention network (W-GAT), for collaborative with We utilize graph attention distance address limitations of LightGCN...