Abstract
Affect interpretation from open-ended drama improvisation is a challenging task. This article describes experiments in using latent semantic analysis to identify discussion themes and potential target audiences for those improvisational inputs without strong affect indicators. A context-based affect-detection is also implemented using a supervised neural network with the consideration of emotional contexts of most intended audiences, sentence types, and interpersonal relationships. In order to go beyond the constraints of predefined scenarios and improve the system's robustness, min-margin-based active learning is implemented. This active learning algorithm also shows great potential in dealing with imbalanced affect classifications. Evaluation results indicated that the context-based affect detection achieved an averaged precision of 0.826 and an averaged recall of 0.813 for affect detection of the test inputs from the Crohn's disease scenario using three emotion labels: positive, negative, and neutral, and an averaged precision of 0.868 and an average recall of 0.876 for the test inputs from the school bullying scenario. Moreover, experimental evaluation on a benchmark data set for active learning demonstrated that active learning was able to greatly reduce human annotation efforts for the training of affect detection, and also showed promising robustness in dealing with open-ended example inputs beyond the improvisation of the chosen scenarios.
- Batliner, A., Steidl, S., Hacker, C., and Nöth, E. 2008. Private emotions vs. social interaction—A data-driven approach towards analysing emotions in speech. In User Modeling and User-Adapted Interaction, 175--206. Google ScholarDigital Library
- Bischoping, K. 1993. Gender differences in conversation topics, 1922--1990. Sex Roles 28, 1/2.Google ScholarCross Ref
- Chen, J., Schein, A., Ungar, L., and Palmer, M. 2006. An empirical study of the behavior of active learning for word sense disambiguation. In Proceedings of the Main Conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics. 120--127. Google ScholarDigital Library
- Ekman, P. 1992. An argument for basic emotions. Cognition Emotion 6, 169--200.Google ScholarCross Ref
- Endrass, B., Rehm, M., and André, E. 2011. Planning small talk behavior with cultural influences for multiagent systems. Comput. Speech Lang. 25, 2, 158--174. Google ScholarDigital Library
- Haffner, P., Tur, G., and Wright, J. 2003. Optimizing SVMs for complex call classification. In Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP).Google Scholar
- Hareli, S. and Rafaeli, A. 2008. Emotion cycles: On the social influence of emotion in organizations. Res. Organiz. Behav. 28, 35--59.Google ScholarCross Ref
- Holub, A., Perona, P., and Burl, M.C. 2008. Entropy-based active learning for object recognition. In Proceedings CVPRW. 1--8.Google Scholar
- Kappas, A. 2010. Smile when you read this, whether you like it or not: Conceptual challenges to affect detection. IEEE Trans. Affective Comput. 1, 1, 38--41. Google ScholarDigital Library
- Landauer, T.K. and Dumais, S. 2008. Latent semantic analysis. Scholarpedia 3, 11, 43--56.Google ScholarCross Ref
- Lewis, D. and Gale, W. 1994. A sequential algorithm for training text classifiers. In Proceedings of the 17th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, New York, 3--12. Google ScholarDigital Library
- Li, H. and Yamanishi, K. 1997. Document classification using a finite mixture model. In Proceedings of Annual Meeting of the Association for Computational Linguistics (ACL-97). Google ScholarDigital Library
- Li, S., Ju, S., Zhou, G., and Li, X. 2012. Active learning for imbalanced sentiment classification. In Proceedings of EMNLP-CoNLL. 139--148. Google ScholarDigital Library
- Manning, C.D. 2011. Part-of-speech tagging from 97% to 100%: Is it time for some linguistics? In Proceedings of CICLing. Lectur Notes in Computer Science, vol. 6608. Springer, Berlin, 171--189. Google ScholarDigital Library
- Mower, E., Metallinou, A., Lee, C., Kazemzadeh, A., Busso, C., Lee, S., and Narayanan, S.S. 2009. Interpreting ambiguous emotional expressions. In Proceedings of the International Conference on Affective Computing and Intelligent Interaction.Google Scholar
- Nahm, U.Y. and Mooney, R.J. 2000. A mutually beneficial integration of data mining and information extraction. In Proceedings of the 17th National Conference on Artificial Intelligence (AAAI 00). 627--632. Google ScholarDigital Library
- Neviarouskaya, A., Prendinger, H., and Ishizuka, M. 2010. Recognition of affect, judgment, and appreciation in text. In Proceedings of the 23rd International Conference on Computational Linguistics. 806--814. Google ScholarDigital Library
- Olsson, F. 2008. Bootstrapping named entity recognition by means of active machine learning. Ph.D. dissertation, University of Gothenburg.Google Scholar
- Ortony, A., Clore, G.L., and Collins, A. 1988. The Cognitive Structure of Emotions. Cambridge University Press.Google Scholar
- Potts, C. and Schwarz, F. 2008. Exclamatives and heightened emotion: Extracting pragmatic generalizations from large corpora. Ms., University of Massachusetts, Amherst.Google Scholar
- Ptaszynski, M., Dybala, P., Shi, W., Rzepka, R., and Araki, K. 2009. Towards context aware emotional intelligence in machines: Computing contextual appropriateness of affective states. In Proceedings of IJCAI. Google ScholarDigital Library
- Russell, J. 1980. A circumplex model of affect. J. Personal.Social Psychol. 39, 6, 1161--1178.Google ScholarCross Ref
- Russell, J.A., Bachorowski, J.A., and Fernandez-Dols, J.M. 2003. Facial and vocal expressions of emotion, Ann. Rev. Psychol. 42, 329--349.Google ScholarCross Ref
- Scherer. K.R. 2003. Vocal communication of emotion: A review of research paradigms. Speech Comm. 40, 227--256. Google ScholarDigital Library
- Shepherd, P. 2012. The emotional response indicator. http://www.trans4mind.com/spiritual/gsr.htm.Google Scholar
- Sun, X. Lichtenauer, J. Valstar, M.F., Nijholt, A., and Pantic, M. 2011. A multimodal database for mimicry analysis. In Proceedings of ACII., 367--376. Google ScholarDigital Library
- Turing, A.M. 1950. Computing machinery and intelligence. Mind, 59, 433--460.Google ScholarCross Ref
- Wang, Z. Lee, J., and Marsella, S. 2011. Towards more comprehensive listening behavior: Beyond the bobble head. In Proceedings of the International Conference on Intelligent Virtual Agents. Google ScholarDigital Library
- Weber, J.S. and Pollack, M.E. 2007. Entropy-driven online active learning for interactive calendar management. In Proceedings of the 12th International Conference on Intelligent User Interfaces. 141--150. Google ScholarDigital Library
- Widdows, D. and Cohen, T. 2010. The semantic vectors package: New algorithms and public tools for distributional semantics. In Proceedings of the IEEE International Conference on Semantic Computing, IEEE, Los Alamitos, CA. Google ScholarDigital Library
- Yu, H. 2005. SVM selective sampling for ranking with application to data retrieval. In Proceedings of the International Conference on Knowledge Discovery and Data Mining (KDD). ACM, New York, 354--363. Google ScholarDigital Library
- Zhang, L. 2010. Exploitation on contextual affect sensing and dynamic relationship interpretation. ACM Comput. Entertain. 8, 3. Google ScholarDigital Library
- Zhang, L., Gillies, M., Dhaliwal, K., Gower, A., Robertson, D., and Crabtree, B. 2009. E-drama: Facilitating online role-play using an AI actor and emotionally expressive characters. Int. J. Artif. Intell .Edu. 19, 1, 5--38. Google ScholarDigital Library
- Zhu, J., Wang, H., Yao, T., and Tsou, B.K. 2008. Active learning with sampling by uncertainty and density for word sense disambiguation and text classification. In Proceedings of the 22nd International Conference on Computational Linguistics (Coling '08). 1137--1144. Google ScholarDigital Library
Index Terms
- Contextual and active learning-based affect-sensing from virtual drama improvisation
Recommendations
Affect detection from semantic and metaphorical interpretation of virtual drama
AAMAS '13: Proceedings of the 2013 international conference on Autonomous agents and multi-agent systemsWe have developed an intelligent agent to engage with users in virtual drama improvisation previously. The agent was able to perform sentence-level affect detection especially from inputs with strong emotional indicators. In this research, we employ ...
Affect detection and an automated improvisational AI actor in E-drama
ICMI'06/IJCAI'07: Proceedings of the ICMI 2006 and IJCAI 2007 international conference on Artifical intelligence for human computingEnabling machines to understand emotions and feelings of the human users in their natural language textual input during interaction is a challenging issue in Human Computing. Our work presented here has tried to make our contribution toward such machine ...
Affect Detection from Virtual Drama
Proceedings of the 26th Australasian Joint Conference on AI 2013: Advances in Artificial Intelligence - Volume 8272We have developed an intelligent agent to engage with users in virtual drama improvisation previously. The intelligent agent was able to perform sentence-level affect detection especially from user inputs with strong emotional indicators. However, we ...
Comments