Help Me Understand This Conversation: Methods of Identifying Implicit Links Between CSCL Contributions
Authors: 
Mihai Masala, Stefan Ruseti, Gabriel Gutu-Robu, Traian Rebedea, Mihai Dascalu, Stefan Trausan-MatuAuthors Info & Claims
Pages 482 - 496
Abstract
Multi-participant chat conversations are one of the most frequently employed Computer Supported Collaborative Learning tools due to their ease of use. Moreover, chats enhance knowledge sharing, sustain creativity and aid in collaborative problem solving. Nevertheless, the manual analysis of multi-participant chats is a difficult task due to the mixture of different topics and the inter-twinning of multiple discussion threads during the same conversation. Several tools that employ Natural Language Processing techniques have been developed to automatically identify links between contributions in order to facilitate the tracking of topics and of discussion threads, as well as to highlight key contributions in terms of follow-up impact. This paper proposes a novel method for detecting implicit links based on features computed using string kernels and word embeddings, combined with neural networks. This method significantly outperforms previous results on the same dataset. Due to its smaller size, our model represents an alternative to more complex deep neural networks, especially when limited training data is available as is the case of CSCL chats in a specific domain.
References
[1]
Stahl G Group Cognition: Computer Support for Building Collaborative Knowledge 2006 Cambridge, MA MIT Press
[2]
Trausan-Matu S Computer support for creativity in small groups using chats Annal. Acad. Rom. Sci. Ser. Sci. Technol. Inf. 2010 3 2 8190
[3]
Holmer T, Kienle A, and Wessner M Nejdl W and Tochtermann K Explicit referencing in learning chats: needs and acceptance Innovative Approaches for Learning and Knowledge Sharing 2006 Heidelberg Springer 170-184
[4]
Manning CD and Schtze H Foundations of Statistical Natural Language Processing 1999 Cambridge, MA MIT Press
[5]
Masala M, Ruseti S, and Rebedea T Sentence selection with neural networks using string kernels Procedia Comput. Sci. 2017 112 1774-1782
[6]
Gutu, G., Dascalu, M., Rebedea, T., Trausan-Matu, S.: Time and semantic similarity what is the best alternative to capture implicit links in CSCL conversations? In: 12th International Conference on Computer-Supported Collaborative Learning (CSCL 2017), pp. 223–230. ISLS (2017)
[7]
Gutu, G., Dascalu, M., Ruseti, S., Rebedea, T., Trausan-Matu, S.: Unlocking the power of word2vec for identifying implicit links. In: 17th IEEE International Conference on Advanced Learning Technologies (ICALT 2017), p. 199200. IEEE (2017)
[8]
Trausan-Matu S and Rebedea T Gelbukh A A polyphonic model and system for inter-animation analysis in chat conversations with multiple participants Computational Linguistics and Intelligent Text Processing 2010 Heidelberg Springer 354-363
[9]
Elsner M and Charniak E Disentangling chat Comput. Linguist. 2010 36 3 389-409
[10]
Miller GA Wordnet: a lexical database for English Commun. ACM 1995 38 11 39-41
[11]
Landauer TK and Dumais ST A solution to plato’s problem: the latent semantic analysis theory of acquisition, induction and representation of knowledge Psychol. Rev. 1997 104 2 211240
[12]
Blei DM, Ng AY, and Jordan MI Latent dirichlet allocation J. Mach. Learn. Res. 2003 3 4–5 9931022
[13]
Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representation in vector space. In: Workshop at ICLR (2013)
[14]
Mehri, S., Carenini, G.: Chat disentanglement: Identifying semantic reply relationships with random forests and recurrent neural networks. In: Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers). vol. 1, pp. 615–623 (2017)
[15]
Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, pp. 3111–3119 (2013)
[16]
Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543 (2014). http://www.aclweb.org/anthology/D14-1162
[17]
Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. arXiv preprint arXiv:1607.04606 (2016)
[18]
Lodhi H, Saunders C, Shawe-Taylor J, Cristianini N, and Watkins C Text classification using string kernels J. Mach. Learn. Res. 2002 2 Feb 419-444
[19]
Ionescu, R.T., Popescu, M., Cahill, A.: Can characters reveal your native language? a language-independent approach to native language identification. In: EMNLP, pp. 1363–1373 (2014)
[20]
Ionescu RT, Popescu M, and Cahill A String kernels for native language identification: insights from behind the curtains Comput. Linguist. 2016 42 491-525
[21]
Gönen M and Alpaydın E Multiple kernel learning algorithms J. Mach. Learn. Res. 2011 12 Jul 2211-2268
[22]
Beck, D., Cohn, T.: Learning kernels over strings using Gaussian processes. In: Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers), vol. 2, pp. 67–73 (2017)
[23]
Bachrach, Y., Zukov-Gregoric, A., Coope, S., Tovell, E., Maksak, B., McMurtie, C.: An attention mechanism for answer selection using a combined global and local view. arXiv preprint arXiv:1707.01378 (2017)
[24]
dos Santos, C.N., Tan, M., Xiang, B., Zhou, B.: Attentive pooling networks. CoRR, abs/1602.03609 (2016)
[25]
Tan, M., dos Santos, C.N., Xiang, B., Zhou, B.: Improved representation learning for question answer matching. In: ACL, vol. 1 (2016)
[26]
Graves, A., Schmidhuber, J.: Framewise phoneme classification with bidirectional LSTM networks. In: Proceedings of 2005 IEEE International Joint Conference on Neural Networks, IJCNN 2005, vol. 4, pp. 2047–2052. IEEE (2005)
[27]
Kim, Y.: Convolutional neural networks for sentence classification. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP 2014), pp. 1746–1751, August 2014
[28]
Wang, S., Jiang, J.: A compare-aggregate model for matching text sequences. arXiv preprint arXiv:1611.01747 (2016)
[29]
Stahl G Studying Virtual Math Teams 2009 New York, NY Springer
[30]
Kingma, D.P., Adam, B.J.: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
[31]
Hu, B., Lu, Z., Li, H., Chen, Q.: Convolutional neural network architectures for matching natural language sentences. In: Advances in neural information processing systems, pp. 2042–2050 (2014)
[32]
Masala M, Ruseti S, Gutu-Robu G, Rebedea T, Dascalu M, and Trausan-Matu S Penstein Rosé C, Martínez-Maldonado R, Hoppe HU, Luckin R, Mavrikis M, Porayska-Pomsta K, McLaren B, and du Boulay B Identifying implicit links in CSCL chats using string kernels and neural networks Artificial Intelligence in Education 2018 Cham Springer 204-208
Recommendations
Promoting socially shared regulation of learning in CSCL
Socially shared regulation plays a critical role in successful collaboration.Process discovery is used to reveal how groups progress in regulated learning.High performing groups evidenced temporal variety in challenges and strategies.Low performing ...
Enhancing non-task sociability of asynchronous CSCL environments
While from a technological perspective Computer Supported Collaborative Learning (CSCL) systems have been improved considerably, previous studies have shown that the social aspect of the CSCL is often neglected or assumed to happen automatically by ...
Patterns for designing planning mechanisms in CSCL environments
Designing and building Computer-Supported Collaborative Learning (CSCL) environments are complex tasks owing to their interdisciplinary characteristics. However, the analysis of CSCL environments presented in the literature shows that it is possible to ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Sep 2018
685 pages
ISBN:978-3-319-98571-8
DOI:10.1007/978-3-319-98572-5
© Springer Nature Switzerland AG 2018.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 03 September 2018
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 12 Jan 2025