Abstract
Chatbots are becoming mainstream. This work aims at ascertaining what are the enablers behind this popularity. To this end, we introduce four quality attributes, namely, “support of a minimal set of commands”, “foresee language variations”, “human-assistance provision” and “timeliness”. These criteria are applied to the 100 most popular Facebook Messenger chatbots. We review and measure both capacities and performance in order to find correlations between quality attribute fulfilment and popularity (chatbots’ ’likes’). Results show no significance correlations between quality attributes and chatbot popularity. However, the experiment comes up with three main contributions. First, a detailed description of how to measure these four quality attributes. Second, insights about how this assessment can be automatized, paving the way towards chatbot-evaluation platforms. Third, a checklist of frequently committed interaction errors as found in the revised chatbots. This might help developers to double-check their development.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Mobile-bots have the push-message ability, updating users with interesting news whenever they happen.
- 2.
Web-bots were implemented ad-hoc, no standard UI was available for them to use, in contrast with mobile-bots running inside well-know apps, like Messenger, Telegram, Skype...
- 3.
- 4.
- 5.
References
Beaver, L.: Chatbots are gaining traction (2017). https://www.businessinsider.com/chatbots-are-gaining-traction-2017-5. Business Insider
Coniam, D.: The linguistic accuracy of chatbots: usability from an ESL perspective. Text Talk 34(5), 545–567 (2014)
Emmet Connolly: Principles of bot design (2016). https://blog.intercom.com/principles-bot-design/. Inside Intercom
Gartner: Chatbots will appeal to Modern Workers (2018). https://www.gartner.com/smarterwithgartner/chatbots-will-appeal-to-modern-workers/
Klüwer, T.: From chatbots to dialog systems. Conversational agents and natural language interaction: techniques and effective practices, pp. 1–22 (2011)
Kuligowska, K.: Commercial chatbot: performance evaluation, usability metrics and quality standards of embodied conversational agents. Prof. Cent. Bus. Res. 2, 1–16 (2015)
Lester, J., Branting, K., Mott, B.: Conversational agents. In: The Practical Handbook of Internet Computing, pp. 220–240 (2004)
de Looper, C.: Facebook is now letting you pay for things through the Messenger Platform, September 2016. https://www.digitaltrends.com/social-media/facebook-messenger-chatbot-payments/
Messina, C.: 2016 will be the year of conversational commerce, January 2016. https://medium.com/chris-messina/2016-will-be-the-year-of-conversational-commerce-1586e85e3991
Morrissey, K., Kirakowski, J.: ‘Realness’ in chatbots: establishing quantifiable criteria. In: Kurosu, M. (ed.) HCI 2013. LNCS, vol. 8007, pp. 87–96. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-39330-3_10
Newlands, M.: Top 10 Practices for Making A Great Chatbot, June 2017. https://www.entrepreneur.com/article/296358
Pauletto, S., et al.: Exploring expressivity and emotion with artificial voice and speech technologies. Logop. Phoniatr. Vocology 38(3), 115–125 (2013)
Pereira, J., Díaz, Ó.: A quality analysis of Facebook Messenger’s most popular chatbots. In: Proceedings of the 33rd ACM/SIGAPP Symposium on Applied Computing, pp. 33:2144–2150 (2018)
Radziwill, N.M., Benton, M.C.: Evaluating Quality of Chatbots and Intelligent Conversational Agents. arXiv preprint arXiv:1704.04579 (2017)
Ramos, R.: Screw the Turing test - chatbots don’t need to act human (2017). https://venturebeat.com/2017/02/03/screw-the-turing-test-chatbots-dont-need-to-act-human/
Goh, O.S., Ardil, C., Wong, W., Fung, C.C.: A black-box approach for response quality evaluation of conversational agent systems. Int. J. Comput. Intell. Syst. 3, 37–41 (2012)
Shawar, B.A., Atwell, E.: Different measurements metrics to evaluate a chatbot system. In: Proceedings of the Workshop on Bridging the Gap: Academic and Industrial Research in Dialog Technologies, pp. 89–96, April 2007
Sullivan, L.: Facebook Chatbots Hit 70% Failure Rate As Consumers Warm Up To The Tech (2017). https://www.mediapost.com/publications/article/295718/facebook-chatbots-hit-70-failure-rate-as-consumer.html
Van Eeuwen, M., Van Der Kaap, H.: Mobile conversational commerce: messenger chatbots as the next interface between businesses and consumers (2017). http://essay.utwente.nl/71706/1/van Eeuwen_MA_BMS.pdf
Wiggers, K.: Facebook Messenger can now find bots, order food, and more (2017). https://www.digitaltrends.com/social-media/facebook-messenger-news-f8-2017/
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Pereira, J., Díaz, Ó. (2019). What Matters for Chatbots? Analyzing Quality Measures for Facebook Messenger’s 100 Most Popular Chatbots. In: Majchrzak, T., Mateos, C., Poggi, F., Grønli, TM. (eds) Towards Integrated Web, Mobile, and IoT Technology. Lecture Notes in Business Information Processing, vol 347. Springer, Cham. https://doi.org/10.1007/978-3-030-28430-5_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-28430-5_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-28429-9
Online ISBN: 978-3-030-28430-5
eBook Packages: Computer ScienceComputer Science (R0)