A Hybrid Deep Learning Technique for Sentiment Analysis in E-Learning Platform with Natural Language Processing

Das, Jay Krishna; Das, Anupam; Rosak-Szyrocka, Joann

doi:10.23919/softcom55329.2022.9911232

Cited by 4 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kim [19] was the first to use a CNN for text tasks, using convolution and pooling operations to extract the representative features in the text and then classifying the sentiment outcomes of the input. Jay et al [20] used a hybrid deep learning model convolutional neural network (CNN) and gated recurrent unit (GRU) to conduct sentiment analysis on e-learning platform text data, which performed well in the classification. Tan et al [21] proposed to use the LSTM-CNN model to extract text semantic information when dealing with answer selection tasks.…”

Section: Research Using Deep Learning Based Approachesmentioning

confidence: 99%

Chinese Multicategory Sentiment of E-Commerce Analysis Based on Deep Learning

Li,

Wang,

et al. 2023

Electronics

View full text Add to dashboard Cite

With the continuous rise of information technology and social networks, and the explosive growth of network text information, text sentiment analysis technology now plays a vital role in public opinion monitoring and product development analysis on networks. Text data are high-dimensional and complex, and traditional binary classification can only classify sentiment from positive or negative aspects. This does not fully cover the various emotions of users, and, therefore, natural language semantic sentiment analysis has limitations. To solve this deficiency, we propose a new model for analyzing text sentiment that combines deep learning and the bidirectional encoder representation from transformers (BERT) model. We first use an advanced BERT language model to convert the input text into dynamic word vectors; then, we adopt a convolutional neural network (CNN) to obtain the relatively significant partial emotional characteristics of the text. After extraction, we use the bidirectional recurrent neural network (BiGRU) to bidirectionally capture the contextual feature message of the text. Finally, with the MultiHeadAttention mechanism we obtain correlations among the data in different information spaces from different subspaces so that the key information related to emotion in the text can be selectively extracted. The final emotional feature representation obtained is classified using Softmax. Compared with other similar existing methods, our model in this research paper showed a good effect in comparative experiments on an e-commerce text dataset, and the accuracy and F1-score of the classification were significantly improved.

show abstract

Section: Research Using Deep Learning Based Approachesmentioning

confidence: 99%

Chinese Multicategory Sentiment of E-Commerce Analysis Based on Deep Learning

Li,

Wang,

et al. 2023

Electronics

View full text Add to dashboard Cite

show abstract

“…According to studies [58,[61][62][63], higher education institutions in different nations are addressing the sustainability problem and may be adjusting the teaching programs they provide in a variety of subjects. Both teachers and pupils need to get significant attention [64]. A technical understanding of inter-and trans-disciplinarity is one thing that educators must possess [63,65].…”

Section: Training Process At a University In Connection With Sustaina...mentioning

confidence: 99%

University 4.0 Sustainable Development in the Way of Society 5.0

et al. 2022

View full text Add to dashboard Cite

Universities can contribute to economic and sustainable development (SD) in a variety of ways, such as mediating social debates, educating citizens on scientific and technical issues, fostering communication among various agents (politicians, businesspeople, higher education institutions’ managers, and citizens), and advancing socioeconomic progress. By teaching the current and next generations of decision-makers, universities have a role in “shaping the ideals of society”. Numerous publications address the topic of sustainable development, but they do so from the standpoint of how its responsibilities are implemented and how students are prepared and aware of it. This manuscript addresses this vacuum by looking at how students assess university activities and specific pillars of sustainable development, which is an unique approach. The investigation used the CAWI questionnaire. The sample consists of 115 Pakistani respondents, and information was gathered between February and August of 2022. The research built a logistic regression model. Our research’s findings and their analysis revealed that University 4.0s should take initiatives for sustainable development, and that these issues are top priorities for them. The analysis revealed that Society 5.0 is active in University 4.0s’ sustainable development initiatives, and that these initiatives are vital for Society 5.0.

show abstract