Skip to main content
SpringerLink
Log in

Knowledge tracing with an intelligent agent, in an e-learning platform

  • Published:
Education and Information Technologies Aims and scope Submit manuscript

Abstract

E-learning systems have gained nowadays a large student community due to the facility of use and the integration of one-to-one service. Indeed, the personalization of the learning process for every user is needed to increase the student satisfaction and learning efficiency. Nevertheless, the number of students who give up their learning process cannot be neglected. Therefore, it is mandatory to establish an efficient way to assess the level of personalization in such systems. In fact, assessing represents the evolution’s key in every personalized application and especially for the e-learning systems. Besides, when the e-learning system can decipher the student personality, the student learning process will be stabilized, and the dropout rate will be decreased. In this context, we propose to evaluate the personalization process in an e-learning platform using an intelligent referential system based on agents. It evaluates any recommendation made by the e-learning platform based on a comparison. We compare the personalized service of the e-learning system and those provided by our referential system. Therefore, our purpose consists in increasing the efficiency of the proposed system to obtain a significant assessment result; precisely, the aim is to improve the outcomes of every algorithm used in each defined agent. This paper deals with the intelligent agent ‘Mod-Knowledge’ responsible for analyzing the student interaction to trace the student knowledge state. The originality of this agent is that it treats the external and the internal student interactions using machine learning algorithms to obtain a complete view of the student knowledge state. The validation of this contribution is done with experiments showing that the proposed algorithms outperform the existing ones.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Notes

  1. Please refer on abbreviations to get the meaning of all used acronyms.

  2. LSTM is a developed version of recurrent neural network that prevent from the vanishing problem using the input/forgot gates.

  3. https://wordnet.princeton.edu/

  4. https://stackexchange.com/

  5. https://stackoverflow.com/questions

  6. https://www.quora.com/

Abbreviations

RPMAS:

Referential Personalized Multi Agent Systems

SOSC:

Stack Overflow for Semantic Correlation

MAE:

Mean Absolute Error

KT:

Knowledge Tracing

ML:

Machine Learning

BKT:

Bayesian Knowledge Tracing

DKT:

Deep Knowledge tracing

LSTM:

Long Short-Term Memory

PFA:

Performance Factor Analysis

DKVMN:

Dynamic Key-Value Memory Net

AIDKVMN:

Augmented Input Dynamic Key-Value Memory Net

LO:

Learning Object

NLP:

Natural Language Processing

IT:

Information Technology

RCNN:

Reccurent Convolutional Neural Network

CNN:

Convolutional Neural Network

SOCSW:

Stack Overflow for Semantic Correlation With verbs

AUC:

Area Under the Curve

References

  • Bollegala, D., Matsuo, Y., Ishizuka, M. (2011). A web search engine-based approach to measure semantic similarity between words. IEEE Transactions on Knowledge and Data Engineering, 23(7), 977–990.

    Article  Google Scholar 

  • Bourkoukou, O., El Bachari, E., El Adnani, M. (2016). A personalized e-learning based on recommender system. International Journal of Learning and Teaching, 2(2), 99–103.

    Google Scholar 

  • Church, K. W., & Hanks, P. (1990). Word association norms, mutual information, and lexicography. Computational Linguistics, 16(1), 22–29.

    Google Scholar 

  • Cilibrasi, R.L., & Vitanyi, P.M.B. (2007). The google similarity distance. IEEE Transactions on Knowledge and Data Engineering, 19(3), 370–383.

    Article  Google Scholar 

  • Corbett, A. T., & Anderson, J. R. (1994). Knowledge tracing: Modeling the acquisition of procedural knowledge. User Modeling and User-Adapted Interaction, 4 (4), 253–278.

    Article  Google Scholar 

  • d Baker, R. S. J., Corbett, A. T., Aleven, V. (2008). More accurate student modeling through contextual estimation of slip and guess probabilities in bayesian knowledge tracing. In International conference on intelligent tutoring systems. (pp. 406–415). Springer.

  • Eirinaki, M., & Vazirgiannis, M. (2003). Web mining for web personalization. ACM Transactions on Internet Technology (TOIT), 3(1), 1–27.

    Article  Google Scholar 

  • Gong, Y., Beck, J. E., Heffernan, N. T. (2010). Comparing knowledge tracing and performance factor analysis by using multiple model fitting procedures. In International conference on intelligent tutoring systems (pp. 35–44). Springer.

  • Guo, Q., & Zhang, M. (2009). Implement web learning environment based on data mining. Knowledge-Based Systems, 22(6), 439–442.

    Article  Google Scholar 

  • Islam, A., Milios, E. E., Keselj, V. (2012). Text similarity using google tri-grams. In Canadian conference on AI (Vol. 7310, pp. 312–317). Springer.

  • Jonassen, D. H., & Grabowski, B. L. (2012). Handbook of individual differences, learning, and instruction. New York: Routledge.

    Google Scholar 

  • Kerns, J. G., Cohen, J. D., MacDonald, A. W., Cho, R. Y., Stenger, V. A., Carter, C. S. (2004). Anterior cingulate conflict monitoring and adjustments in control. Science, 303(5660), 1023–1026.

    Article  Google Scholar 

  • Khamparia, A., & Pandey, B. (2015). Knowledge and intelligent computing methods in e-learning. International Journal of Technology Enhanced Learning, 7(3), 221–242.

    Article  Google Scholar 

  • Kim, Y. (2014). Convolutional neural networks for sentence classification. arXiv:http://arXiv.org/abs/1408.5882.

  • Lai, S., Xu, L., Liu, K., Zhao, J. (2015). Recurrent convolutional neural networks for text classification. In AAAI (Vol. 333, pp. 2267–2273).

  • Lin, D. (1998). Others an information-theoretic definition of similarity. In Icml (Vol. 98, pp. 296–304).

  • Liu, B., Feng, J., Liu, M., Liu, F., Wang, X., Li, P. (2014). Computing semantic relatedness using a word-text mutual guidance model. In Natural language processing and Chinese computing (pp. 67–78). Springer.

  • Pascanu, R., Mikolov, T., Bengio, Y. (2013). On the difficulty of training recurrent neural networks. In International conference on machine learning (pp. 1310–1318).

  • Pavlik, Jr, P. I., Cen, H., Koedinger, K. R. (2009). Performance factors analysis–a new alternative to knowledge tracing. Online Submission.

  • Pekrun, R., Elliot, A. J., Maier, M. A. (2009). Achievement goals and achievement emotions: Testing a model of their joint relations with academic performance. Journal of Educational Psychology, 101(1), 115.

    Article  Google Scholar 

  • Pérez Martínez, C., López Morteo, G., Martínez Reyes, M., Gelbukh, A. (2015). Wikipedia-based learning path generation. Computación y Sistemas, 19 (3), 589–600.

    Article  Google Scholar 

  • Piech, C., Bassen, J., Huang, J., Ganguli, S., Sahami, M., Guibas, L. J., Sohl-Dickstein, J. (2015). Deep knowledge tracing. In Advances in neural information processing systems (pp. 505–513).

  • Salonen, V., & Karjaluoto, H. (2016). Web personalization: the state of the art and future avenues for research and practice. Telematics and Informatics, 33(4), 1088–1104.

    Article  Google Scholar 

  • Senach, B. (1990). Evaluation ergonomique des interfaces homme-machine: une revue de la littėrature. PhD thesis, INRIA.

  • Trifa, A., Sbai, A. H., Chaari, W. L. (2017a). Enhancing assessment of personalized multi-agent system through convLSTM. Procedia Computer Science, 112, 249–259.

  • Trifa, A., Sbai, A. H., Chaari, W. L. (2017b). Evaluate a personalized multi agent system through social networks: web scraping. In 2017 IEEE 26th international conference on enabling technologies: infrastructure for collaborative enterprises (WETICE) (pp. 18–20). IEEE.

  • Tu̇rker, A., Gȯrgu̇n, B., Conlan, O. (2006). The challenge of content creation to facilitate personalized e-learning experiences. International Journal on ELearning, 5(1), 11.

    Google Scholar 

  • Wu, Z., & Palmer, M. (1994). Verbs semantics and lexical selection . In Proceedings of the 32nd annual meeting on association for computational linguistics (pp. 133–138). Association for Computational Linguistics.

  • Xiong, X., Zhao, S., Van Inwegen, E., Beck, J. (2016). Going deeper with deep knowledge tracing. In EDM (pp. 545–550).

  • Zack, M. H. (2009). Knowledge and strategy. New York: Routledge.

    Book  Google Scholar 

  • Zapata, A., Menėndez, V. H., Prieto, M. E., Romero, C. (2015). Evaluation and selection of group recommendation strategies for collaborative searching of learning objects. International Journal of Human-Computer Studies, 76, 22–39.

    Article  Google Scholar 

  • Zhang, J., Shi, X., King, I., Yeung, D. -Y. (2017). Dynamic key-value memory networks for knowledge tracing. In Proceedings of the 26th international conference on World Wide Web (pp. 765–774). International World Wide Web Conferences Steering Committee.

  • Zheng, Y., Li, L., Zheng, F. (2010). An analysis framework of activity context in e-learning environments. Entertainment for Education. Digital Techniques and Systems, 6249, 258–268.

    Google Scholar 

  • Zhuhadar, L., & Nasraoui, O. (2008). Semantic information retrieval for personalized e-learning. In 2008. ICTAI’08. 20th IEEE international conference on tools with artificial intelligence (Vol. 1, pp. 364–368). IEEE.

Download references

Author information

Authors and Affiliations

  1. Artificial Intelligence, Cosmos Lab, National School of Computer Sciences, Manouba, Tunisia

    Amal Trifa, Aroua Hedhili & Wided Lejouad Chaari

Authors
  1. Amal Trifa
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Aroua Hedhili
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Wided Lejouad Chaari
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Amal Trifa.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendix

Appendix

We expose in this part the different student’s knowledge evolution during the learning process, regarding some exercises, realized on six different related learning objects. The kept knowledge is detected after applying respectively DKVMN algorithm and AIDKVMN algorithm on the gathered data. The Fig. 11 shows those results for one user. In fact, we notice that the “0” level of knowledge detected in one learning object in the Fig. 11a is unrelated to the previous states of the student knowledge regarding the LO. This signifies that either the answered question doesn’t have any relation to the LO or that student doesn’t know the response. The Fig. 11b shows that the detected “0” are surrounded by low knowledge level. This explicates student attempts to go beyond his relatively limited knowledge thanks to interactions on external forums or external e-learning platforms. Each added interaction in the Fig. 11b decreases the difference between near states in each learning object. This is very logic as the hidden information, used in our algorithm has a great impact on deciphering the student knowledge evolution. It can further help to detect the student perturbation on performing certain tasks concerning some LO(s).

Fig. 11
figure 11

The student knowledge evolution between the first case (I), representing the DKVMN algorithm applied on the partial observed data, and the second case (II), representing the AIDKVMN algorithm applied on all obtained data

Full size image
Fig. 12
figure 12

The SOCSW flowchart

Full size image
Fig. 13
figure 13

AIDKVMN flowchart

Full size image

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Trifa, A., Hedhili, A. & Chaari, W.L. Knowledge tracing with an intelligent agent, in an e-learning platform. Educ Inf Technol 24, 711–741 (2019). https://doi.org/10.1007/s10639-018-9792-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10639-018-9792-5

Keywords

Search

Navigation