CoChat
Sign Up
Cited by 133Online Learning and AnalyticsIntelligent Tutoring Systems and Adaptive LearningArtificial Intelligence in Education

Natural Language Generation Using Deep Learning to Support MOOC Learners

Open access
Li, Chenglu, Xing, Wanli·2021·International Journal of Artificial Intelligence in Education
DOI 10.1007/s40593-020-00235-x
Open this paper in CoChat — free accountOpen PDF

Abstract

Among all the learning resources within MOOCs such as video lectures and homework, the discussion forum stood out as a valuable platform for students’ learning through knowledge exchange. However, peer interactions on MOOC discussion forums are scarce. The lack of interactions among MOOC learners can yield negative effects on students’ learning, causing low participation and high dropout rate. This research aims to examine the extent to which the deep-learning-based natural language generation (NLG) models can offer responses similar to human-generated responses to the learners in MOOC forums. Specifically, under the framework of social support theory, this study has examined the use of state-of-the-art deep learning models recurrent neural network (RNN) and generative pretrained transformer 2 (GPT-2) to provide students with informational, emotional, and community support with NLG on discussion forums. We first trained an RNN and GPT-2 model with 13,850 entries of post-reply pairs. Quantitative evaluation on model performance was then conducted with word perplexity, readability, and coherence. The results showed that GPT-2 outperformed RNN on all measures. We then qualitatively compared the dimensions of support provided by humans and GPT-2, and the results suggested that the GPT-2 model can comparably provide emotional and community support to human learners with contextual replies. We further surveyed participants to find out if the collected data would align with our findings. The results showed GPT-2 model could provide supportive and contextual replies to a similar extent compared to humans.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1007/s40593-020-00235-x

Cites

5 of 5 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • AI language models provide a platform for asynchronous communication, which has been found to increase student engagement and collaboration.

    “One of the main advantages of artificial intelligence language model is that they provide a platform for asynchronous communication.This feature has been found to increase student engagement and collaboration, as it allows students to post questions and discuss topics without having to be present at the same time (Li & Xing, 2021).”

    From Chatting and cheating: Ensuring academic integrity in the era of ChatGPT (2024) · cites this paper as Li & Xing, 2021

    The Introduction (page unavailable) describes MOOC discussion forums as platforms for knowledge exchange and reports that peer support in those forums benefits engagement. The Discussion (page unavailable) says the AI models generate replies to forum posts, not that the models themselves provide an asynchronous platform. The paper does not establish that using the models increases student engagement or collaboration. (LLM, conf=0.85)

    Experimental — accuracy not yet measured

  • LLMs are capable of providing effective emotional support to students, fostering a more positive learning experience.

    “a study by Li and Xing (2021) found that LLMs were capable of providing effective emotional support to students, helping to foster a more positive learning experience.”

    From Generative AI and Essay Writing: Impacts of Automated Feedback on Revision Performance and Engagement (2024) · cites this paper as Li and Xing, 2021

    The Discussion (page unavailable) says GPT-2-generated replies could provide a similar extent of emotional support to human replies. The Conclusion (page unavailable) describes the work as preliminary and improved engagement as a possible future result; it does not establish that students experienced a more positive learning experience. (LLM, conf=0.88)

    Experimental — accuracy not yet measured

  • Li and Xing (2021) demonstrated that LLM-based feedback can have a statistically significant and positive impact on students' affective experiences and emotional well-being.

    “This finding contrasts with previous studies, such as those by Li and Xing (2021), which demonstrated that LLM-based feedback can have a statistically significant and positive impact on students' affective experiences and emotional well-being.”

    From Generative AI and Essay Writing: Impacts of Automated Feedback on Revision Performance and Engagement (2024) · cites this paper as Li and Xing (2021)

    The Discussion (page unavailable) says GPT-2-generated replies provided emotional support comparable to human replies. But the Results for Multidimensional Support from GPT-2 (page unavailable) found no significant difference in emotional support between the two; the study evaluated replies, not a positive impact on students’ affective experiences or emotional well-being. (LLM, conf=0.87)

    Experimental — accuracy not yet measured

  • One study has discussed potential risk of adopting underperforming models, which could negatively affect students' learning experiences.

    “For example, one study has discussed the potential risk of adopting underperforming models, which could negatively affect students' learning experiences (Li & Xing, 2021).”

    From Practical and ethical challenges of large language models in education: A systematic scoping review (2024) · cites this paper as Li & Xing, 2021

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 87

  1. Adelani, D. I., Mai, H., Fang, F., Nguyen, H. H., Yamagishi, J., & Echizen, I. (2020). Generating sentiment- preserving fake online reviews using neural language models and their human-and machine-based detection. In International Conference on Advanced Information Networking and Applications (pp. 1341-1354). Cham: Springer.
  2. Alimova, I., & Tutubalina, E. (2020). Multiple features for clinical relation extraction: A machine learning approach. Journal of Biomedical Informatics, 103, 103382.
  3. Almatrafi, O., Johri, A., & Rangwala, H. (2018). Needle in a haystack: Identifying learner posts that require urgent response in MOOC discussion forums. Computers & Education, 118, 1-9. https://doi.org/10.1016/ j.compedu.2017.11.002. · DOI
  4. Babori, A., Zaid, A., & Fassi, H. F. (2019). Research on MOOCs in major referred journals. The International Review of Research in Open and Distributed Learning, 20, 3. https://doi.org/10.19173/irrodl.v20i4.4385. · DOI
  5. Benamara, F., & Saint-Dizier, P. (2004). Advanced relaxation for cooperative question answering. In M. T. Maybury (Ed.), New directions in question answering (pp. 263-274). Menlo Park: AAAI Press.
  6. Bengio, Y., Ducharme, R., Vincent, P., & Jauvin, C. (2003). A neural probabilistic language model. Journal of Machine Learning Research, 3, 1137-1155 http://www.jmlr.org/papers/volume3/bengio03a/bengio03a. pdf. Accessed 10 December 2019.
  7. Budzianowski, P., & Vulić, I. (2019). Hello, It's GPT-2-How can I help you? Towards the use of pretrained language models for task-oriented dialogue systems. In A. Birch, A. Finch, H. Hayashi, I. Konstas, T. Luong, G. Neubig, Y. Oda, & K. Sudoh (Eds), Proceedings of the 3rd Workshop on Neural Generation and Translation (pp. 15-22). Association for Computational Linguistics. https://doi.org/10.18653/v1/ d19-5602. · DOI
  8. Caballé, S., & Conesa, J. (2019). Conversational Agents in Support for Collaborative Learning in MOOCs: An Analytical Review. In F. Xhafa, L. Barolli, & M. Greguš (Eds.), Advances in Intelligent Networking and Collaborative Systems. INCoS 2018. Lecture notes on data engineering and communications technologies (Vol. 23). Cham: Springer.
  9. Chiu, T. K., & Hew, T. K. (2018). Factors influencing peer learning and performance in MOOC asynchronous online discussion forum. Australasian Journal of Educational Technology, 34(4), 16-28. https://doi.org/ 10.14742/ajet.3240. · DOI
  10. Clark, E., Celikyilmaz, A., Smith, N. A. (2019). Sentence mover's similarity: Automatic evaluation for multi- sentence texts. In A. Korhonen, D. Traum, & L. Màrquez (Eds), Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2748-2760. Association for Computational Linguistics. doi:https://doi.org/10.18653/v1/P19-1264. · DOI
  11. Cleveland-Innes, M., & Campbell, P. (2012). Emotional presence, learning, and the online learning environ- ment. The International Review of Research in Open and Distributed Learning, 13(4), 269-292.
  12. Cutrona, C. E., & Russell, D. W. (1990). Type of social support and specific stress: Toward a theory of optimal matching. In B. R. Sarason, I. G. Sarason, & G. R. Pierce (Eds.), Wiley series on personality processes. Social support: An interactional view (pp. 319-366). New York: John Wiley & Sons. Retrieved 10 Jan 2020, from https://psycnet.apa.org/record/1990-97699-013.
  13. Dale, R. (2016). The return of the chatbots. Natural Language Engineering, 22(5), 811-817. https://doi.org/ 10.1017/S1351324916000243. · DOI
  14. Deetjen, U., & Powell, J. A. (2016). Informational and emotional elements in online support groups: A Bayesian approach to large-scale content analysis. Journal of the American Medical Informatics Association, 23(3), 508-513. https://doi.org/10.1093/jamia/ocv190. · DOI
  15. Demetriadis, S., Tegos, S., Psathas, G., Tsiatsos, T., Weinberger, A., Caballé, S., … Karakostas, A. (2018). Conversational Agents as Group-Teacher Interaction Mediators in MOOCs. Proceedings of 2018 Learning With MOOCS (LWMOOCS), 43-46. https://doi.org/10.1109/lwmoocs.2018.8534686. · DOI
  16. Dubosson, M., & Emad, S. (2015). The forum community, the Connectivist element of an xMOOC. Universal Journal of Educational Research, 3(10), 680-690. https://doi.org/10.13189/ujer.2015.031004. · DOI
  17. Dufty, D. F., Graesser, A. C., Louwerse, M. M., McNamara, D. S. (2006). Assigning grade levels to textbooks: Is it just readability? Proceedings of the Annual Meeting of the Cognitive Science Society, 28, 1251-1256. Retrieved 10 Jan 2020, from https://escholarship.org/uc/item/44f184z9.
  18. Evans, R., Piwek, P., Cahill, L. (2002). What is NLG? Proceedings of the International Natural Language Generation Conference, 144-151. Retrieved 21 Dec 2019, from https://www.aclweb.org/anthology/W02- 2119.pdf.
  19. Evermann, J., Rehse, J.-R., & Fettke, P. (2016). A deep learning approach for predicting process behaviour at runtime. In M. Dumas, & M. Fantinato (Eds), Proceedings of International Conference on Business Process Management, Vol. 281 (pp. 327-338). Springer. https://doi.org/10.1007/978-3-319-58457-7_24. · DOI
  20. Fang, A., Macdonald, C., Ounis, I., & Habel, P. (2016). Using word embedding to evaluate the coherence of topics from twitter data. Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, 1057-1060. https://doi.org/10.1145/2911451.2914729. · DOI
  21. Fedus, W., Goodfellow, I., & Dai, A. M. (2018). MaskGAN: Better text generation via filling in the_. ArXiv Preprint ArXiv, 1801, 07736.
  22. Feng, L., Jansche, M., Huenerfauth, M., Elhadad, N. (2010). A comparison of features for automatic readability assessment. Proceedings of the 23rd International Conference on Computational Linguistics: Posters, 276-284. Retrieved 24 Dec 2019, from https://dl.acm.org/doi/pdf/10.5555/ 1944566.1944598. · DOI
  23. Ferschke, O., Yang, D., Tomar, G., Rosé, C. P. (2015). Positive impact of collaborative chat participation in an edX MOOC. In C. Conati, N. Heffernan, A. Mitrovic, & M. Verdejo (Eds), Proceedings of International Conference on Artificial Intelligence in Education, Vol. 9112, 115-124. Springer. https://doi.org/10.1007/ 978-3-319-19773-9_12. · DOI
  24. Goldie, J. G. S. (2016). Connectivism: A knowledge learning theory for the digital age? Medical Teacher, 38(10), 1064-1069. https://doi.org/10.3109/0142159X.2016.1173661. · DOI
  25. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. Cambridge: MIT press.
  26. Graves, A. (2013). Generating sequences with recurrent neural networks. ArXiv Preprint ArXiv, 1308, 0850.
  27. Hew, K. F. (2016). Promoting engagement in online courses: What strategies can we learn from three highly rated MOOCS. British Journal of Educational Technology, 47(2), 320-341. https://doi.org/10.1111/bjet.12235. · DOI
  28. House, J. S. (1981). Work stress and social support. Massachusetts: Addison-Wesley.
  29. Hsu, J.-Y., Chen, C.-C., & Ting, P.-F. (2018). Understanding MOOC continuance: An empirical examination of social support theory. Interactive Learning Environments, 26(8), 1100-1118. https://doi.org/10.1080/ 10494820.2018.1446990. · DOI
  30. Io, H. N., & Lee, C. B. (2017). Chatbots and conversational agents: Proceedings of 2017 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM), 215-219. https://doi.org/ 10.1109/ieem.2017.8289883. · DOI
  31. Jung, Y., & Lee, J. (2018). Learning engagement and persistence in massive open online courses (MOOCS). Computers & Education, 122, 9-22. https://doi.org/10.1016/j.compedu.2018.02.013. · DOI
  32. Kincaid, J. P., Fishburne Jr, R. P., Rogers, R. L., Chissom, B. S. (1975). Derivation of new readability formulas (automated readability index, fog count and flesch reading ease formula) for navy enlisted personnel. Institute for Simulation and Training, University of Central Florida. https://doi.org/10.21236/ ada006655. · DOI · Paper page
  33. Kop, R., Fournier, H., & Mak, J. S. F. (2011). A pedagogy of abundance or a pedagogy to support human beings? Participant support on massive open online courses. The International Review of Research in Open and Distributed Learning, 12(7), 74-93. https://doi.org/10.19173/irrodl.v12i7.1041. · DOI
  34. Kumar, R., & Rose, C. P. (2010). Architecture for building conversational agents that support collaborative learning. IEEE Transactions on Learning Technologies, 4(1), 21-34. https://doi.org/10.1109/TLT.2010. · DOI · Paper page
  35. Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., & Soricut, R. (2019). Albert: A lite bert for self- supervised learning of language representations. ArXiv Preprint ArXiv, 1909, 11942. · DOI · Paper page
  36. Langford, C. P. H., Bowsher, J., Maloney, J. P., & Lillis, P. P. (1997). Social support: A conceptual analysis. Journal of Advanced Nursing, 25(1), 95-100. https://doi.org/10.1046/j.1365-2648.1997.1997025095.x. · DOI
  37. LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521, 436-444. https://doi.org/10.1038/ nature14539. · DOI · Paper page
  38. Lee, Y., & Choi, J. (2011). A review of online course dropout research: Implications for practice and future research. Educational Technology Research and Development, 59(5), 593-618. https://doi.org/10.1007/ s11423-010-9177-y. · DOI · Paper page
  39. Lee, J. S., & Hsiang, J. (2019). Patent claim generation by fine-tuning openai GPT-2. ArXiv preprint arXiv, 1907, 02052.
  40. Lin, C.-P., & Anol, B. (2008). Learning online social support: An investigation of network information technology based on UTAUT. Cyberpsychology & Behavior, 11(3), 268-272. https://doi.org/10.1089/ cpb.2007.0057. · DOI
  41. Lipari, M., Berlie, H., Saleh, Y., Hang, P., & Moser, L. (2019). Understandability, actionability, and readability of online patient education materials about diabetes mellitus. American Journal of Health- System Pharmacy, 76(3), 182-186.
  42. Mackness, J., Waite, M., Roberts, G., & Lovegrove, E. (2013). Learning in a small, task-oriented, connectivist MOOC: Pedagogical issues and implications for higher education. The International Review of Research in Open and Distributed Learning, 14(4), 140-159.
  43. Masters, K. (2011). A brief guide to understanding MOOCs. The Internet Journal of Medical Education, 1(2), 1-6. https://doi.org/10.5580/1f21. · DOI
  44. McKeown, K. R. (1982). The TEXT system for natural language generation: An overview. Proceedings of the 20th Annual Meeting on Association for Computational Linguistics, 113-120. https://doi.org/10.3115/ 981251.981285. · DOI
  45. McNamara, D. S., Graesser, A. C., McCarthy, P. M., Cai, Z. (2014). Automated evaluation of text and discourse with Coh-Metrix. Cambridge University Press. https://doi.org/10.1017/cbo9780511894664. · DOI
  46. Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S., Dean, J. (2013a). Distributed representations of words and phrases and their compositionality. In C. Burges, L. Bottou, M. Welling, Z. Ghahramani, & K. Weinberger (Eds), Advances in Neural Information Processing Systems: Vol. 26 (pp. 3111-3119).
  47. Mikolov, T., Yih, W. T., Zweig, G. (2013b). Linguistic regularities in continuous space word representations. In R. Morante & S. Yih (Eds), Proceedings of the 2013 conference of the north american chapter of the association for computational linguistics: Human language technologies (pp. 746-751). Association for Computational Linguistics. https://doi.org/10.3115/v1/w14-1618. · DOI
  48. Mittal, A., Vigentini, L., Djatmiko, M., Prusty, G., Sharma, Y., King, M. E. (2018). MOOC-O-Bot: Using Cognitive Technologies to Extend Knowledge Support in MOOCs. Proceedings of the 2018 IEEE International Conference on Teaching, Assessment, and Learning for Engineering (TALE), 69-76. https://doi.org/10.1109/tale.2018.8615453. · DOI
  49. Moore, R. L., Oliver, K. M., & Wang, C. (2019). Setting the pace: Examining cognitive processing in MOOC discussion forums with automatic text analysis. Interactive Learning Environments, 27(5-6), 655-669. https://doi.org/10.1080/10494820.2019.1610453. · DOI
  50. Ortega-Arranz, A., Bote-Lorenzo, M. L., Asensio-Pérez, J. I., Martínez-Monés, A., Gómez-Sánchez, E., & Dimitriadis, Y. (2019). To reward and beyond: Analyzing the effect of reward-based strategies in a MOOC. Computers & Education, 142, 103639. https://doi.org/10.1016/j.compedu.201. · DOI
  51. Pereira, J. (2016). Leveraging chatbots to improve self-guided learning through conversational quizzes. In F. J. García-Peñalvo (Ed), Proceedings of theFourth International Conference on Technological Ecosystems for Enhancing Multiculturality, (911-918). Association for Computing Machinery. https://doi.org/10. 1145/3012430.3012625. · DOI
  52. Pietquin, O., & Hastie, H. (2013). A survey on metrics for the evaluation of user simulations. The Knowledge Engineering Review, 28(1), 59-73. https://doi.org/10.1017/S0269888912000343. · DOI
  53. Potash, P., Romanov, A., Rumshisky, A. (2015). Ghostwriter: Using an lstm for automatic rap lyric generation. In L. Màrquez, C. Callison-Burch, & J. Su (Eds), Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, 1919-1924. Association for Computational Linguistics. https://doi.org/10.18653/v1/d15-1221. · DOI
  54. Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I. (2019). Language models are unsupervised multitask learners. OpenAI Blog, 1(8), 9. Retrieved 28 Dec 2019, from http://www.persagen.com/files/ misc/radford2019language.pdf.
  55. Radziwill, N. M., & Benton, M. C. (2017). Evaluating quality of chatbots and intelligent conversational agents. ArXiv Preprint ArXiv, 1704, 04579.
  56. Roitero, K., Bozzato, C., Mizzaro, V. D. M. S., Serra, G. (2020). Twitter goes to the Doctor: Detecting Medical Tweets using Machine Learning and BERT. In F. Couto & M. Krallinger (Eds), Proceedings of the Workshop on Semantic Indexing and Information Retrieval for Health from heterogeneous content types and languages co-located with 42nd European Conference on Information Retrieval: Vol. 2619. RWTH Aachen University. Retrieved 4 Dec 2019, from http://ceur-ws.org/Vol-2619/short1.pdf.
  57. Ruey, S. (2010). A case study of constructivist instructional strategies for adult online learning. British Journal of Educational Technology, 41(5), 706-720. https://doi.org/10.1111/j.1467-8535.2009.00965.x. · DOI · Paper page
  58. Serban, I., Sordoni, A., Bengio, Y., Courville, A., & Pineau, J. (2016). Building end-to-end dialogue systems using generative hierarchical neural network models. Proceedings of the AAAI Conference on Artificial Intelligence, 30(1), 3776-3783. Retrieved 2 Jan 2020, from https://dl.acm.org/doi/10.5555/3016387. 3016435. · DOI
  59. Shah, D. (2019). Online degrees slowdown: A Review of MOOC Stats and Trends in 2019 -Class central. Class central Retrieved 4 Jan 2020, from https://www.classcentral.com/report/moocs-stats-and-trends- 2019.
  60. Shawar, B. A., & Atwell, E. (2007a). Different measurements metrics to evaluate a chatbot system. Proceedings of the Workshop on Bridging the Gap: Academic and Industrial Research in Dialog Technologies, 89-96. https://doi.org/10.3115/1556328.1556341. · DOI
  61. Shawar, B. A., & Atwell, E. (2007b). Chatbots: Are they really useful? Journal for Language Technology and Computational Linguistics, 22(1), 29-49.
  62. Shumaker, S. A., & Brownell, A. (1984). Toward a theory of social support: Closing conceptual gaps. Journal of Social Issues, 40(4), 11-36. https://doi.org/10.1111/j.1540-4560.1984.tb01105.x. · DOI
  63. Silverman, T. (1999). The internet and relational theory. American Psychologist, 54, 780-781. https://doi.org/ 10.1037/0003-066X.54.9.780. · DOI
  64. Sordoni, A., Galley, M., Auli, M., Brockett, C., Ji, Y., Mitchell, M., et al. (2015). A neural network approach to context-sensitive generation of conversational responses. ArXiv Preprint ArXiv, 1506, 06714.
  65. Sunar, A. S., White, S., Abdullah, N. A., & Davis, H. C. (2016). How learners' interactions sustain engagement: A MOOC case study. IEEE Transactions on Learning Technologies, 10(4), 475-487. https://doi.org/10.1109/TLT.2016.2633268. · DOI
  66. Tagliamonte, S. A., & Denis, D. (2008). Linguistic ruin? LOL! Instant messaging and teen language. American speech, 83(1), 3-34.
  67. Tang, S., Peterson, J. C., Pardos, Z. A. (2016). Deep neural networks and how they apply to sequential education data. Proceedings of the Third ACM Conference on Learning@ Scale Conference, 321- 324. https://doi.org/10.1145/2876034.2893444. · DOI
  68. Tegos, S., Psathas, G., Tsiatsos, T., Demetriadis, S. N. (2019). Designing Conversational Agent Interventions that Support Collaborative Chat Activities in MOOCs. In M. Calise, C. Kloos, C. Mongenet, J. Reich, J. Ruipérez-Valiente, G. Shimshon, T. Staubitz, & M. Wirsing (Eds), Proceedings of Proceedings of Work in Progress Papers of the Research, Experience and Business Tracks at EMOOCs 2019: Vol. 2356 (pp. 66-71). Retrieved 20 Dec 2019, from http://ceur-ws.org/Vol-2356/research_short11.pdf.
  69. Tomkin, J. H., & Charlevoix, D. (2014). Do professors matter?: Using an a/b test to evaluate the impact of instructor involvement on MOOC student outcomes. Proceedings of the First ACM Conference on Learning@ Scale Conference, 71-78. https://doi.org/10.1145/2556325.2566245. · DOI
  70. Tsai, H. S., Shillair, R., & Cotten, S. R. (2017). Social support and "playing around" an examination of how older adults acquire digital literacy with tablet computers. Journal of Applied Gerontology, 36(1), 29-55. https://doi.org/10.1177/0733464815609440. · DOI
  71. Vakulenko, S., de Rijke, M., Cochez, M., Savenkov, V., & Polleres, A. (2018). Measuring semantic coherence of a conversation. In International semantic web conference (pp. 634-651). Cham: Springer.
  72. Guyon, U. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, & R. Garnett (Eds), Advances in Neural Information Processing Systems: Vol. 30 (pp. 5998-6008).
  73. Wang, X., Yang, D., Wen, M., Koedinger, K., Rosé, C. P. (2015). Investigating how Student's cognitive behavior in MOOC discussion forums affect learning gains. In O. C. Santos, J. G. Boticario, C. Romero, M. Pechenizkiy, A. Merceron, P. Mitros, J. M. Luna, C. Mihaescu, P. Moreno, A. Hershkovitz, S. Ventura, & M. Desmarais (Eds), Proceedings of the 8th International Conference on Educational Data Mining (pp. 226-233). International Educational Data Mining Society. Retrieved 2 Jan 2020, from https:// files.eric.ed.gov/fulltext/ED560568.pdf.
  74. Wang, W., Gan, Z., Wang, W., Shen, D., Huang, J., Ping, W., ... & Carin, L. (2018). Topic compositional neural language model. In A. Storkey & F. Perez-Cruz (Eds), Proceedings of Machine Learning Research: Vol. 84. International Conference on Artificial Intelligence and Statistics (pp. 356-365). Retrieved 23 Dec 2019, from http://proceedings.mlr.press/v84/wang18a/wang18a.pdf.
  75. Wen, M., Yang, D., Rose, C. (2014). Sentiment analysis in MOOC discussion forums: What does it tell us? In J. Stamper, Z. Pardos, M. Mavrikis, & B.M. McLaren (Eds.), Proceedings of the 7th International Conference on Educational Data Mining (pp. 130-137). Retrieved 2 Jan 2020, from http://citeseerx.ist. psu.edu/viewdoc/download?doi=10.1.1.660.5804&rep=rep1&type=pdf.
  76. Wen, T. H., Gašic, M., Mrkšic, N., Rojas-Barahona, L. M., Su, P. H., Vandyke, D., Young, S. (2015). Toward multi-domain language generation using recurrent neural networks. In K. Knight, A. Nenkova, & O. Rambow (Eds), Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (pp. 120-129). Association for Computational Linguistics. https://doi.org/10.18653/v1/N16-1015. · DOI
  77. Wills, T. A. (1991). Social support and interpersonal relationships. In M. S. Clark (Ed.), Review of personality and social psychology, Vol. 12. Prosocial behavior (pp. 265-289). Thousand Oaks: Sage Publications, Inc..
  78. Wise, A. F., Cui, Y., Jin, W., & Vytasek, J. (2017). Mining for gold: Identifying content-related MOOC discussion threads across domains through linguistic modeling. The Internet and Higher Education, 32, 11-28. https://doi.org/10.1016/j.iheduc.2016.08.001. · DOI
  79. Wu, M., Xu, X., Kang, L., Zhao, J. L., & Liang, L. (2019). Encouraging people to embrace feedback-seeking in online learning: An investigation of informational and relational drivers. Internet Research, 29(4), 749- 771. https://doi.org/10.1108/IntR-04-2017-0162. · DOI
  80. Xing, W. (2019). Exploring the influences of MOOC design features on student performance and persistence. Distance Education, 40(1), 98-113. https://doi.org/10.1080/01587919.2018.1553560. · DOI
  81. Xing, W., & Du, D. (2019). Dropout prediction in MOOCs: Using deep learning for personalized intervention. Journal of Educational Computing Research, 57(3), 547-570. https://doi.org/10.1177/ 0735633118757015. · DOI
  82. Xing, W., Chen, X., Stein, J., & Marcinkowski, M. (2016). Temporal predication of dropouts in MOOCs: Reaching the low hanging fruit through stacking generalization. Computers inhuman behavior, 58, 119- 129. https://doi.org/10.1016/j.chb.2015.12.007. · DOI
  83. Xing, W., Goggins, S., & Introne, J. (2018). Quantifying the effect of informational support on membership retention in online communities through large-scale data analytics. Computers in Human Behavior, 86, 227-234. https://doi.org/10.1016/j.chb.2018.04.042. · DOI
  84. Xu, W., Napoles, C., Pavlick, E., Chen, Q., & Callison-Burch, C. (2016). Optimizing statistical machine translation for text simplification. Transactions of the Association for Computational Linguistics, 4, 401- 415. https://doi.org/10.1162/tacl_a_00107. · DOI
  85. Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R., & Le, Q. V. (2019). XLNet: Generalized autoregressive Pretraining for language understanding. ArXiv Preprint ArXiv, 1906, 08237.
  86. Zhang, Y., Sun, S., Galley, M., Chen, Y.-C., Brockett, C., Gao, X., … Dolan, B. (2020). DialoGPT: Large- scale generative pre-training for conversational response generation. In A. Celikyilmaz, T. Wen (Eds), Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (pp. 270-278). Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.acl-demos. · DOI · Paper page
  87. Zumbrunn, S., McKim, C., Buhs, E., & Hawley, L. R. (2014). Support, belonging, motivation, and engagement in the college classroom: A mixed method study. Instructional Science, 42(5), 661-684. https://doi.org/10.1007/s11251-014-9310-0. · DOI · Paper page

Cited by

Sorted by citations

Authors
Li, C., & Xing, W.
Affiliations
University of Florida (US)
Corresponding author
Xing, Wanli
ORCID
Venue
International Journal of Artificial Intelligence in Education
Publisher
Elsevier BV
Published
2021-06
Volume
31
Issue
2
Pages
186-214
ISSN
1560-4292 (ISSN-L)
DOI
10.1007/s40593-020-00235-x
OpenAlex
W3121259022
Cited by
133
References
5
Citations by year
2026: 14 · 2025: 28 · 2024: 40 · 2023: 32 · 2022: 13 · 2021: 6
FWCI
19.26
Type
journal article
Language
en
Open access
Licence
Locations
International Journal of Artificial Intelligence in Education (publishedVersion, cc-by-nc-nd)
Topics
  • Physical Sciences › Computer Science › Computer Science Applications › Online Learning and Analytics
  • Physical Sciences › Computer Science › Artificial Intelligence › Intelligent Tutoring Systems and Adaptive Learning
  • Physical Sciences › Computer Science › Information Systems › Artificial Intelligence in Education
Keywords
natural language generation, MOOC discussion forums, GPT-2, recurrent neural networks, social support theory, peer interaction, learner dropout, emotional support, community support, information support

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review