Journal of Intelligence and Information Systems (지능정보연구)

Korea Intelligent Information System Society (한국지능정보시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Identifying Social Relationships using Text Analysis for Social Chatbots

소셜챗봇 구축에 필요한 관계성 추론을 위한 텍스트마이닝 방법

  • 김정훈 (경희대학교 일반대학원 경영학과) ;
  • 권오병 (경희대학교 일반대학원 경영학과)
  • Received : 2018.08.24
  • Accepted : 2018.12.16
  • Published : 2018.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

A chatbot is an interactive assistant that utilizes many communication modes: voice, images, video, or text. It is an artificial intelligence-based application that responds to users' needs or solves problems during user-friendly conversation. However, the current version of the chatbot is focused on understanding and performing tasks requested by the user; its ability to generate personalized conversation suitable for relationship-building is limited. Recognizing the need to build a relationship and making suitable conversation is more important for social chatbots who require social skills similar to those of problem-solving chatbots like the intelligent personal assistant. The purpose of this study is to propose a text analysis method that evaluates relationships between chatbots and users based on content input by the user and adapted to the communication situation, enabling the chatbot to conduct suitable conversations. To evaluate the performance of this method, we examined learning and verified the results using actual SNS conversation records. The results of the analysis will aid in implementation of the social chatbot, as this method yields excellent results even when the private profile information of the user is excluded for privacy reasons.

챗봇은 음성, 이미지, 비디오 또는 텍스트와 같은 다양한 매채를 이용하여 대화가 가능한 대화형 어시스턴트이자 인공지능을 기반으로 사용자의 질문에 답하거나 문제를 해결할 수 있는 사용자 친화적 프로그램이다. 하지만 현재 챗봇은 사용자가 요청한 작업을 정확하게 수행하는 기술적측면에 초점이 맞추어져 있으며, 개인화된 대화로 사용자와 챗봇간의 관계성 구축에는 제한적이어서 일부 사례에도 불구하고 소셜챗봇이 되기에는 미흡한 상태이다. 만약 인간의 사회성을 나타내는 특징 중 하나인 관계성을 챗봇이 인식하여 알맞게 대화를 하여 문제를 해결할 수 있다면, 개인화된 대화를 할 수 있을 뿐만 아니라 인간과 유사한 대화를 할 수 있을 것이다. 본 연구의 목적은 사용자가 입력한 내용을 기반으로 챗봇과 사용자 간의 관계성을 추론하고 대화 상황에 맞게 대화 상대가 적절한 대화를 수행 할 수 있는 텍스트 분석 방법을 제안하는 것이다. 본 연구의 실험 및 평가를 하기 위하여 실제 SNS대화 내용을 사용하였다. 분석결과 개인정보 보호를 위해 사용자의 개인 프로필 정보가 제외된 방법에서도 우수한 결과를 나타내어 소셜 챗봇에 적합한 방법으로 검증되었다.

Keywords

JJSHBB_2018_v24n4_85_f0001.png 이미지

Research Framework

JJSHBB_2018_v24n4_85_f0002.png 이미지

Data Preparation Procedure

JJSHBB_2018_v24n4_85_f0003.png 이미지

Examples of Relationship Inferencing during Conversation

JJSHBB_2018_v24n4_85_f0004.png 이미지

Aggregated Data by Session

JJSHBB_2018_v24n4_85_f0005.png 이미지

Performance Comparison

Related Studies on Relationship Inferencing

JJSHBB_2018_v24n4_85_t0001.png 이미지

Class and Input Features

JJSHBB_2018_v24n4_85_t0002.png 이미지

Input Features in Inferred User Profile

JJSHBB_2018_v24n4_85_t0003.png 이미지

Input Features in Inferred User Context

JJSHBB_2018_v24n4_85_t0004.png 이미지

Relation Frequency

JJSHBB_2018_v24n4_85_t0005.png 이미지

Sample text by Relation

JJSHBB_2018_v24n4_85_t0006.png 이미지

Results of Logistic Regression Analysis

JJSHBB_2018_v24n4_85_t0007.png 이미지

Performance Comparison (Overall Accuracy)

JJSHBB_2018_v24n4_85_t0008.png 이미지

References

  1. Al-Zubaide, H., and Issa, A. A, "Ontbot: Ontology based chatbot," Innovation in Information & Communication Technology (ISIICT), 2011 Fourth International Symposium on IEEE, (2011, November), 7-12.
  2. Araujo, T., "Living up to the chatbot hype: The influence of anthropomorphic design cues and communicative agency framing on conversational agent and company perceptions," Computers in Human Behavior, Vol.85(2018), 183-189. https://doi.org/10.1016/j.chb.2018.03.051
  3. Breazeal, C., "Regulation and entrainment in human-robot interaction," The International Journal of Robotics Research, Vol.21, Issue.10-11(2002), 883-902. https://doi.org/10.1177/0278364902021010096
  4. Cassell, J., J. Sullivan, S. Prevost and E. Churchill, "Embodied Conversational Agents," Cambridge,MA: MIT Press, 2000.
  5. Cerekovic, A., Aran, O., and D.Gatica-Perez, "Rapport with virtual agents: What do human social cues and personality explain?,". IEEE Transactions on Affective Computing, Vol.8, Issue.3(2017), 382-395. https://doi.org/10.1109/TAFFC.2016.2545650
  6. Colby K.M, "Human-Computer Conversation in A Cognitive Therapy Program" In: Wilks Y. (eds) Machine Conversations. The Springer International Series in Engineering and Computer Science, vol 511. Springer, Boston, MA,1999.
  7. Choi, S., Jeon, J., Subrata, B., Kwon, O., "An efficient estimation of place brand image power based on text mining technology," Journal of Korea Intelligent Information Systems, Vol. 21, No.2(2015), 113-129. https://doi.org/10.13088/jiis.2015.21.2.113
  8. Choi, S. Song, Y., Kwon, O., "Analyzing contextual polarity of unstructured data for measuring subjective well-being," Journal of Intelligent Information Systems, Vol.22, No.1(2016), 83-105. https://doi.org/10.13088/jiis.2016.22.1.083
  9. Cui, M., Jin, Y. and Kwon, O., "A method of analyzing sentiment polarity of multilingual social media : A case of korean-chinese languages," Journal of Intelligent Information Systems, Vol.22, No.3(2016), 91-111. https://doi.org/10.13088/jiis.2016.22.3.091
  10. Diehl, C. P., Namata, G., and Getoor, L, Relationship identification for social network discovery, In AAAI ,Vol. 22, No. 1(2007, July), 546-552,.
  11. Faratin, P., C.Sierra, and N. R.Jennings, "Negotiation decision functions for autonomous," agents. Robotics and Autonomous Systems, Vol.24, No.3-4(1998), 159-182. https://doi.org/10.1016/S0921-8890(98)00029-3
  12. Griol, D., J.Carbo, and J. M.Molina, "An automatic dialog simulation technique to develop and evaluate interactive conversational agents,". Applied Artificial Intelligence, Vol.27, No.9(2013), 759-780. https://doi.org/10.1080/08839514.2013.835230
  13. Haslam, N. and A.P. Fiske" Relational models theory: a confirmatory factor analysis," Personal Relationships, Vol.6, No.2(1999), 241-250. https://doi.org/10.1111/j.1475-6811.1999.tb00190.x
  14. Hill, J., W. R.Ford, and I. G.Farreras, "Real conversations with artificial intelligence: A comparison between human-human online conversations and human-chatbot conversations," Computers in Human Behavior, Vol.49(2015), 245-250. https://doi.org/10.1016/j.chb.2015.02.026
  15. Hirschberg, J, and C. D.Manning,, "Advances in natural language processing," Science, Vol.349(2015), 261-266. https://doi.org/10.1126/science.aaa8685
  16. Hung, V., M.Elvir, A.Gonzalez, and R.DeMara, "Towards a method for evaluating naturalness in conversational dialog systems," In Systems, Man and Cybernetics, 2009. SMC 2009. IEEE International Conference on, (2009, October), 1236-1241.
  17. Jamieson, L. "Intimacy transformed? A critical look at the 'pure relationship'," Sociology, Vol.33(1999), 477-494.
  18. Jong, A. D., and K.De Ruyter, "Adaptive versus proactive behavior in service recovery: the role of self‐managing teams," Decision Sciences, Vol.35(2004), 457-491. https://doi.org/10.1111/j.0011-7315.2004.02513.x
  19. Kirkpatrick, L. A. and B. J. Ellis. An Evolutionary-Psychological Approach to Self-esteem: Multiple Domains and Multiple Functions, Blackwell handbook of social psychology, Interpersonal processes, 409-436, 2001.
  20. Koerner, A.F, "Models of relating - not relationship models: cognitive representations of relating across interpersonal relationship domains," Journal of Social and Personal Relationships, Vol.23(2006), 629-653. https://doi.org/10.1177/0265407506065989
  21. Kuligowska, K, "Commercial chatbot: Performance evaluation, usability metrics, and quality standards of embodied conversational agents," Professionals Center for Business Research 2, 2015.
  22. Kwon, O, "A two-step approach to building bilateral consensus between agents based on relationship learning theory," Expert Systems with Applications, Vol.36, No.9(2009), 11957-11965. https://doi.org/10.1016/j.eswa.2009.03.070
  23. Kwon, O., and N. Lee, "A relationship‐aware methodology for context‐aware service selection," Expert Systems, Vol.28, No.4 (2011), 375-390. https://doi.org/10.1111/j.1468-0394.2010.00548.x
  24. Lindgaard,G, "The misapplication of engineering models to business decisions," INTERACT'03, Zurich, Switzerland, (2003), 367-374.
  25. Lopez-Monroy, A. P., M.Montes-y-Gomez, H. J.Escalante, L.Villasenor-Pineda, and E.Stamatatos, "Discriminative subprofilespecific representations for author profiling in social media," Knowledge-Based Systems, Vol.89(2015), 134-147. https://doi.org/10.1016/j.knosys.2015.06.024
  26. Madhu, D., Jain, C. N., Sebastain, E., Shaji, S., and A.Ajayakumar, "A novel approach for medical assistance using trained chatbot," In Inventive Communication and Computational Technologies (ICICCT), 2017 International Conference on, (2017, March), 243-246.
  27. Nielsen, J, Usability heuristics, in Usability Engineering, Academic Press, 1994, 115-164.
  28. Oliver, R. L, Satisfaction: A Behavioral Perspective on the Consumer: A Behavioral Perspective on the Consumer. Routledge, 2014.
  29. Perera, C., A.Zaslavsky, P.Christen, and D.Georgakopoulos, Context aware computing for the internet of things: A survey, IEEE Communications Surveys & Tutorials, Vol.16, No.1(2014), 414-454. https://doi.org/10.1109/SURV.2013.042313.00197
  30. Pham, D. D., G. B.Tran, and S. B. Pham,. "Author profiling for Vietnamese blogs," In Asian Language Processing, 2009. IALP'09. International Conference on, (2009, December), 190-194).
  31. Reddy, T. R., B. V.Vardhan, and P. V.Reddy, "Profile specific Document Weighted approach using a New Term Weighting Measure for Author Profiling," International Journal of Intelligent Engineering & Systems, (2016), 136-146.
  32. Reeves, B. and C. Nass, The Media Equation: How People Treat Computers, Television, and New Media Like Real People and Places, Cambridge: Cambridge University Press, 1996.
  33. Sandbank, T., M.Shmueli-Scheuer, D.Konopnicki, , J.Herzig, J.Richards, and D.Piorkowski, "Detecting Egregious Conversations between Customers and Virtual Agents," arXiv preprint arXiv:1711.05780., 2017.
  34. Seo, H., and Kwon, O. Mining Intellectual History Using Unstructured Data Analytics to Classify Thoughts for Digital Humanities. Journal of Intelligent Information Systems, Vol.24, No.1(2018), 141-166.
  35. Shawar, B. A., and E.Atwell, "Different measurements metrics to evaluate a chatbot system," Proceedings of the Workshop on Bridging the Gap: Academic and Industrial Research in Dialog Technologies, (2007, April), 89-96.
  36. Shum, H. Y., X. D. He, and D. Li, From Eliza to XiaoIce: challenges and opportunities with social chatbots. Frontiers of Information Technology & Electronic Engineering, Vol.19, No.1(2018), 10-26. https://doi.org/10.1631/FITEE.1700826
  37. Stevenson, M, "Individual Profiling Using Text Analysis," University of Sheffield, Sheffield United Kingdom, 2016.
  38. Tan, L., and N.Wang, (2010, August). "Future internet: The internet of things," In Advanced Computer Theory and Engineering (ICACTE), 2010 3rd International Conference on, Vol. 5 (2010, August), V5-376.
  39. Villegas, M. P., M. J.Garciarena Ucelay, M. L.Errecalde, and L.Cagnina, "A Spanish text corpus for the author profiling task," XX Congreso Argentino de Ciencias de la Computacion, (Buenos Aires, 2014).
  40. Wang, C., J. Han, Y. Jia, J.Tang, D. Zhang, Y. Yu, and J. Guo, "Mining advisor-advisee relationships from research publication networks," Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining, (2010, July), 203-212.
  41. Weizenbaum, J, "ELIZA-A computer program for the study of natural language communication between man and machine," Communications of the ACM. Vol. 10, No. 8(1966), 36-45.
  42. Yu, C., N. Wang, L. T.Yang, , D. Yao, C. H.Hsu, and H. Jin "A semi-supervised social relationships inferred model based on mobile phone data," Future Generation Computer Systems, Vol.76(2017), 458-467. https://doi.org/10.1016/j.future.2016.11.027
  43. Yu, Z., X. Zhou, D. Zhang, G. Schiele, and C. Becker, "Understanding social relationship evolution by using real-world sensing data," World Wide Web, Vol.16, No.5-6(2013), 749-762. https://doi.org/10.1007/s11280-012-0189-x
  44. Zhuang, H., J. Tang, W. Tang, T. Lou, A. Chin, and X. Wang, "Actively learning to infer social ties," Data Mining and Knowledge Discovery, Vol.25, No.2(2012), 270-297. https://doi.org/10.1007/s10618-012-0274-x