Sentiment Analysis of Online Course Evaluation Based on a New Ensemble Deep Learning Mode: Evidence from Chinese
Source abstract
Abstract
In recent years, online course learning has gradually become the mainstream of learning. As the key data reflecting the quality of online courses, users’ comments are very important for improving the quality of online courses. The sentiment information contained in comments is the guide of course improvement. A new ensemble model is proposed for sentiment analysis. The model takes full advantage of Word2Vec and Glove in word vector representation, and utilizes the bidirectional long and short time network and convolutional neural network to achieve deep feature extraction. Moreover, the multi-objective gray wolf optimization (MOGWO) ensemble method is adopted to integrate the models mentioned above. The experimental results show that the sentiment recognition accuracy of the proposed model is higher than that of the other seven comparison models, with an F1score over 91%, and the recognition results of different emotion levels indicate the stability of the proposed ensemble model.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Sentiment Analysis and Opinion Mining · Online Learning and Analytics · Advanced Computing and Algorithms
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Information Engineering, Hunan Industry Polytechnic, Changsha 410036, China
School of Traffic and Transportation Engineering, Central South University, Changsha 410075, China
School of Traffic and Transportation, Beijing Jiaotong University, Beijing 100044, China
References (58)
Show source-provided references
1. Over 200 million students being taught online in China during COVID-19: Will online teaching become the routine model in medical education?10.1016/j.asjsur.2021.01.034 ↗
2. Identifying patterns of epistemic emotions with respect to interactions in massive online open courses using deep learning and social network analysis10.1016/j.chb.2021.106843 ↗
3. Young children’s online learning during COVID-19 pandemic: Chinese parents’ beliefs and attitudes10.1016/j.childyouth.2020.105440 ↗
4. The effect of online review exercises on student course engagement and learning performance: A case study of an introductory financial accounting course at an international joint venture university10.1016/j.jaccedu.2020.100699 ↗
5. The evaluation of online course of Traditional Chinese Medicine for Medical Bachelor, Bachelor of Surgery international students during the COVID-19 epidemic period10.1016/j.imr.2020.100449 ↗
6. Sentiment Analysis of Weibo Comment Texts Based on Extended Vocabulary and Convolutional Neural Network10.1016/j.procs.2019.01.239 ↗
7. Sentiment analysis of Chinese micro-blog text based on extended sentiment dictionary10.1016/j.future.2017.09.048 ↗
8. Important citation identification using sentiment analysis of in-text citations10.1016/j.tele.2020.101492 ↗
9. Widyassari, A.P., Rustad, S., Shidik, G.F., Noersasongko, E., Syukur, A., Affandy, A., and Setiadi, D.R.I.M. (2020). Review of automatic text summarization techniques & methods. J. King Saud Univ.—Comput. Inf. Sci., in press.
10. Deep Learning-Based Sentiment Analysis for Roman Urdu Text10.1016/j.procs.2019.01.202 ↗
11. Deep Learning for Aspect-Based Sentiment Analysis: A Comparative Review10.1016/j.eswa.2018.10.003 ↗
12. Kumhar, S.H., Kirmani, M.M., Sheetlani, J., and Hassan, M. (2021). Word Embedding Generation for Urdu Language using Word2vec model. Mater. Today Proc., in press.10.1016/j.matpr.2020.11.766 ↗
13. FastTalker: A neural text-to-speech architecture with shallow and group autoregression10.1016/j.neunet.2021.04.016 ↗
14. A constrained optimization algorithm for learning GloVe embeddings with semantic lexicons10.1016/j.knosys.2020.105628 ↗
15. Sentimental Short Sentences Classification by Using CNN Deep Learning Model with Fine Tuned Word2Vec10.1016/j.procs.2020.03.416 ↗
16. A recent overview of the state-of-the-art elements of text classification10.1016/j.eswa.2018.03.058 ↗
17. Representation learning: A review and new perspectives10.1109/TPAMI.2013.50 ↗
18. Mikolov, T., Corrado, G., Kai, C., and Dean, J. (2013). Efficient Estimation of Word Representations in Vector Space. arXiv.
19. Sentiment aware word embeddings using refinement and senti-contextualized learning approach10.1016/j.neucom.2020.03.094 ↗
20. Two-Stage Topic Extraction Model for Bibliometric Data Analysis Based on Word Embeddings and Clustering10.1109/ACCESS.2019.2945911 ↗
21. Sentiment Analysis Using Word2vec And Long Short-Term Memory (LSTM) For Indonesian Hotel Reviews10.1016/j.procs.2021.01.061 ↗
22. Pennington, J., Socher, R., and Manning, C.D. (2014, January 25–29). Glove: Global vectors for word representation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar.10.3115/v1/D14-1162 ↗
23. Calibrating GloVe model on the principle of Zipf’s law10.1016/j.patrec.2019.07.015 ↗
24. Content Tree Word Embedding for document representation10.1016/j.eswa.2017.08.021 ↗
25. Adaptive cross-contextual word embedding for word polysemy with unsupervised topic modeling10.1016/j.knosys.2021.106827 ↗
26. LearningToAdapt with word embeddings: Domain adaptation of Named Entity Recognition systems10.1016/j.ipm.2021.102537 ↗
27. Khan, J., and Lee, Y.K. (2019). LeSSA: A Unified Framework based on Lexicons and Semi-Supervised Learning Approaches for Textual Sentiment Classification. Appl. Sci., 9.10.3390/app9245562 ↗
28. Wunderlich, F., and Memmert, D. (2020). Innovative Approaches in Sports Science-Lexicon-Based Sentiment Analysis as a Tool to Analyze Sports-Related Twitter Communication. Appl. Sci., 10.10.3390/app10020431 ↗
29. The evolution of sentiment analysis—A review of research topics, venues, and top cited papers10.1016/j.cosrev.2017.10.002 ↗
30. Text mining with sentiment analysis on seafarers’ medical documents
31. SACPC: A framework based on probabilistic linguistic terms for short text sentiment analysis10.1016/j.knosys.2020.105572 ↗
32. Chinese sentiment classification based on Word2vec and vector arithmetic in human–robot conversation10.1016/j.compeleceng.2021.107423 ↗
33. Tran, T.K., and Phan, T.T. (2019). Deep Learning Application to Ensemble Learning-The Simple, but Effective, Approach to Sentiment Classifying. Appl. Sci., 9.10.3390/app9132760 ↗
34. Han, K.X., Chien, W., Chiu, C.C., and Cheng, Y.T. (2020). Application of Support Vector Machine (SVM) in the Sentiment Analysis of Twitter DataSet. Appl. Sci., 10.10.3390/app10031125 ↗
35. Deep learning for Arabic subjective sentiment analysis: Challenges and research opportunities10.1016/j.asoc.2020.106836 ↗
36. Multi-level graph neural network for text sentiment analysis10.1016/j.compeleceng.2021.107096 ↗
37. An algorithm and method for sentiment analysis using the text and emoticon10.1016/j.icte.2020.07.003 ↗
38. Prospecting Information Extraction by Text Mining Based on Convolutional Neural Networks–A Case Study of the Lala Copper Deposit, China10.1109/ACCESS.2018.2870203 ↗
39. Dong, S., Yu, C., Yan, G., Zhu, J., and Hu, H. (2021, January 12–14). A Novel ensemble reinforcement learning gated recursive network for traffic speed forecasting. Proceedings of the 2021 Workshop on Algorithm and Big Data, Fuzhou, China.10.1145/3456389.3456397 ↗
40. Multi-label classification with weighted classifier selection and stacked ensemble10.1016/j.ins.2020.06.017 ↗
41. Non-intrusive classification of gas-liquid flow regimes in an S-shaped pipeline riser using a Doppler ultrasonic sensor and deep neural networks10.1016/j.cej.2020.126401 ↗
42. Minakova, S., and Stefanov, T. (2020, January 26–28). Buffer sizes reduction for memory-efficient CNN inference on mobile and embedded devices. Proceedings of the 2020 23rd Euromicro Conference on Digital System Design (DSD 2020), Kranj, Slovenia.10.1109/DSD51259.2020.00031 ↗
43. Yan, G., Yu, C., and Bai, Y. (2021). Wind Turbine Bearing Temperature Forecasting Using a New Data-Driven Ensemble Approach. Machines, 9.10.3390/machines9110248 ↗
44. Learning deep features to recognise speech emotion using merged deep CNN10.1049/iet-spr.2017.0320 ↗
45. Cai, H.J., and Chen, T. (October, January 26). Multi-dimension CNN for hyperspectral image classificaton. Proceedings of the IGARSS 2020—2020 IEEE International Geoscience and Remote Sensing Symposium, Waikoloa, HI, USA.10.1109/IGARSS39084.2020.9323561 ↗
46. A new multi-data-driven spatiotemporal PM2. 5 forecasting model based on an ensemble graph reinforcement learning convolutional network10.1016/j.apr.2021.101197 ↗
47. A Residual BiLSTM Model for Named Entity Recognition10.1109/ACCESS.2020.3046253 ↗
48. Liao, F., Ma, L.L., and Yang, D.J. (2019, January 9–11). Research on Construction Method of Knowledge Graph of US Military Equipment Based on BiLSTM model. Proceedings of the 2019 International Conference on High Performance Big Data and Intelligent Systems (HPBD&IS), Shenzhen, China.10.1109/HPBDIS.2019.8735478 ↗
49. Ma, W., Yu, H.Z., Zhao, K., Zhao, D.S., Yang, J., and Ma, J. (2019, January 17–19). Tibetan location name recognition based on BiLSTM-CRF model. Proceedings of the 2019 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CYBERC), Guilin, China.10.1109/CyberC.2019.00077 ↗
50. Zhang, P.F., Li, F.H., Du, L.D., Zhao, R.J., Chen, X.X., Yang, T., and Fang, Z. (2021). Psychological Stress Detection According to ECG Using a Deep Learning Model with Attention Mechanism. Appl. Sci., 11.10.3390/app11062848 ↗
51. Chen, W.J., and Li, J.L. (2021). Forecasting Teleconsultation Demand Using an Ensemble CNN Attention-Based BILSTM Model with Additional Variables. Healthcare, 9.10.3390/healthcare9080992 ↗
52. Du, J., Cheng, Y.Y., Zhou, Q.A., Zhang, J.M., Zhang, X.Y., Li, G., and IOP (2019, January 15–16). Power load forecasting using BiLSTM-attention. Proceedings of the 2019 5th International Conference on Environmental Science and Material Application, Xi’an, China.
53. Multi-objective grey wolf optimizer based on decomposition10.1016/j.eswa.2018.12.003 ↗
54. Enhanced leadership-inspired grey wolf optimizer for global optimization problems10.1007/s00366-019-00795-0 ↗
55. Ling, O.Y., Theng, L.B., Chai, A., and McCarthy, C. (2018, January 23–25). A model for automatic recognition of vertical texts in natural scene images. Proceedings of the 2018 8th IEEE International Conference on Control System, Computing and Engineering (ICCSCE 2018), Penang, Malaysia.10.1109/ICCSCE.2018.8685019 ↗
56. Liu, M.F., Xie, Z.C., Huang, Y.X., Jin, L.W., and Zhou, W.Y. (2018, January 5–8). Distilling GRU with data augmentation for unconstrained handwritten text recognition. Proceedings of the 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), Niagara Falls, NY, USA.10.1109/ICFHR-2018.2018.00019 ↗
57. Nguyen, H.T., Nguyen, C.T., and Nakagawa, M. (2018, January 5–8). ICFHR 2018-competition on Vietnamese online handwritten text recognition using HANDS-VNOnDB (VOHTR2018). Proceedings of the 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), Niagara Falls, NY, USA.10.1109/ICFHR-2018.2018.00092 ↗
58. Qin, Y., and Zhang, Z. (2020, January 9–13). Summary of scene text detection and recognition. Proceedings of the 15th IEEE Conference on Industrial Electronics and Applications (ICIEA 2020), Kristiansand, Norway.10.1109/ICIEA48937.2020.9248121 ↗