Understanding the Adoption of Chatbot

A Case Study of Siri
  • Hio Nam Io
  • Chang Boon Lee
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 886)


Due to a recent development in artificial intelligence (AI) and natural language processing, chatbots can understand the human language much better than before. E-commerce businesses are beginning to adopt chatbots in their operations, in areas, such as customer service, product inquiry and transaction refund, etc. However, there is still a lack of studies on users’ adoption of chatbots, and businesses are uncertain how to develop chatbots that will increase users’ adoption. The purpose of this study is to use sentiment analysis to understand the adoption of chatbots. This study used Siri-related comments posted on the social networking site Weibo during the period January 2017 to July 2017 to conduct the sentiment analysis. The results reveal that users generally had positive emotions with Siri and they used Siri mainly because they wanted to ‘come on to’ or ‘take liberties with’ the chatbot. In this study, we also compared Siri and Alime, which is a chatbot developed by Alibaba. This study then explored how the results of the sentiment analysis can be applied to the development of chatbots.


Chatbot Siri Sentiment analysis Alime Adoption Electronic commerce 


  1. 1.
    Qiu, M., Li, F.L., Wang, S.Y., Gao, X., Chen, Y.: AliMe Chat: A sequence to sequence and rerank based chatbot engine. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pp. 498–503 (2017)Google Scholar
  2. 2.
    Weizenbaum, J.: ELIZA—a computer program for the study of natural language communication between man and machine. Commun. ACM 9(1), 36–45 (1966)CrossRefGoogle Scholar
  3. 3.
    Shah, H., Warwick, K., Vallverdú, J., Wu, D.: Can machines talk? Comparison of Eliza with modern dialogue systems. Comput. Hum. Behav. 58, 278–295 (2016)CrossRefGoogle Scholar
  4. 4.
    Holotescu, C.: MOOCBuddy: a chatbot for personalized learning with MOOCs. In: Rochi – International Conference on Human-Computer Interaction, vol. 8, pp. 91–94 (2016)Google Scholar
  5. 5.
    Shawar, B.A., Atwell, E.: A comparison between ALICE and Elizabeth chatbot systems. Raport instytutowy, University of Leeds (2002)Google Scholar
  6. 6.
    Ngo, T.L., Pham, K.L., Cao, M.S., Pham, S.B., Phan, X.H.: Dialogue Act Segmentation for Vietnamese Human-Human Conversational Texts. arXiv preprint, arXiv:1708.04765 (2017)
  7. 7.
    Li, Y.: Deep Reinforcement Learning: An Overview,” arXiv preprint, arXiv:1701.07274 (2017)
  8. 8.
    Li, J.W., Monroe, W., Ritter, A., Galley, M., Gao, J.F., Jurafsky, D.: Deep Reinforcement Learning for Dialogue Generation, arXiv preprint, arXiv:1606.01541 (2017)
  9. 9.
    LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436–444 (2015)CrossRefGoogle Scholar
  10. 10.
    Chen, Y.N., Hakkani-Tür, D., Tur, G., Gao, J.F., Deng, L.: End-to-end memory networks with knowledge carryover for multi-turn spoken language understanding. In: INTERSPEECH (2016)Google Scholar
  11. 11.
    Aye, Y.M., Aung, S.S.: Sentiment analysis for reviews of restaurants in Myanmar text. In: 2017 18th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD), Kanazawa, Japan, pp. 321–326 (2017)Google Scholar
  12. 12.
    Maharani, W.: Microblogging sentiment analysis with lexical based and machine learning approaches. In: 2013 International Conference of Information and Communication Technology (ICoICT), Bandung, pp. 439–443 (2013)Google Scholar
  13. 13.
    Aizawa, A.: An information-theoretic perspective of TF-IDF measures. Inf. Process. Manag. 39, 45–65 (2003)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of Accounting and Information ManagementUniversity of MacauMacauChina

Personalised recommendations