A5079501434- Online Learning and Analytics
- Topic Modeling
- Sentiment Analysis and Opinion Mining
- Advanced Graph Neural Networks
- Recommender Systems and Techniques
- Text and Document Classification Technologies
- Intelligent Tutoring Systems and Adaptive Learning
- Analog and Mixed-Signal Circuit Design
- Web Data Mining and Analysis
- Experimental Learning in Engineering
- Natural Language Processing Techniques
Wuhan University of Technology
2019-2021
Zhejiang University
2021
The growing prosperity of social networks has brought great challenges to the sentimental tendency mining users. As more and researchers pay attention online users, rich research results have been obtained based on sentiment classification explicit texts. However, implicit users is still in its infancy. Aiming at difficulty classification, a model deep neural network carried out. Classification models DNN, LSTM, Bi-LSTM CNN were established judge user's text. Based model, word-level...
There is thereby an urgent need but it still a significant challenge to solve long Chinese t ext sentiment. BERT-based pre-trained language model (PLM) has been demonstrated be the state-of-the-art approach for sentiment analysis. However, BERT can only process 510 tokens at time, limiting accuracy of analysis texts. Meanwhile, existing text truncation methods this deficiency perform weak in capture core sentiments. Aiming better analysis, we propose fusion model. Firstly, elaborately devise...
The outbreak of the COVID-19 pandemic arises enormous attention to online education then knowledge tracking is an increasingly crucial task with its vigorous development.However, surge student historical interactions and lack prior engendering a sequence issues, such as decrease in prediction accuracy while increase training time.Simultaneously, most existing approaches fail provide in-depth insights into why likely answer question incorrectly what affects state student.To address those we...
The growing prosperity of social networks has brought great challenges to the sentimental tendency mining users. As more and researchers pay attention online users, rich research results have been obtained based on sentiment classification explicit texts. However, implicit users is still in its infancy. Aiming at difficulty classification, a model deep neural network carried out. Classification models DNN, LSTM, Bi-LSTM CNN were established judge user's text. Based model, word-level...
Massive Online Open Courses (MOOC) have popularized educational opportunities for students all over the world, while immensely high dropout is becoming a central challenge nowadays.Most researches predict course labels through analyzing student engagement data.However, these models structural complexity with time cost and cannot provide in-depth insights into why likely to drop out.We devise lightweight pipeline simplify MOOC problem, grasp core features make behaviours interpretable at...