ABSTRACT
Emotion analysis of online customer service conservation is important for good user experience and customer satisfaction. However, conventional metrics do not fit this application scenario. In this work, by collecting and labeling online conversations of customer service on Twitter, we identify 8 new metrics, named as tones, to describe emotional information. To better interpret each tone, we extend the Latent Dirichlet Allocation (LDA) model to Tone LDA (T-LDA). In T-LDA, each latent topic is explicitly associated with one of three semantic categories, i.e., tone-related, domain-specific and auxiliary. By integrating tone label into learning, T-LDA can interfere the original unsupervised training process and thus is able to identify representative tone-related words. In evaluation, T-LDA shows better performance than baselines in predicting tone intensity. Also, a case study is conducted to analyze each tone via T-LDA output.
- Jennifer L Aaker. 1997. Dimensions of brand personality. Journal of marketing research (1997), 347--356.Google Scholar
- Apoorv Agarwal, Boyi Xie, Ilia Vovsha, Owen Rambow, and Rebecca Passonneau. 2011. Sentiment analysis of twitter data. In Proceedings of the workshop on languages in social media. Association for Computational Linguistics, 30--38. Google ScholarDigital Library
- David Andrzejewski and Xiaojin Zhu. 2009. Latent dirichlet allocation with topic-in-set knowledge Proceedings of the NAACL HLT 2009 Workshop on Semi-Supervised Learning for Natural Language Processing. Association for Computational Linguistics, 43--48. Google ScholarDigital Library
- David M Blei, Andrew Y Ng, and Michael I Jordan. 2003. Latent dirichlet allocation. Journal of machine Learning research Vol. 3, Jan (2003), 993--1022. Google ScholarDigital Library
- Johan Bollen, Huina Mao, and Xiaojun Zeng. 2011. Twitter mood predicts the stock market. Journal of computational science Vol. 2, 1 (2011), 1--8.Google ScholarCross Ref
- Laurence Devillers, Lori Lamel, and Ioana Vasilescu. 2003. Emotion detection in task-oriented spoken dialogues Multimedia and Expo, 2003. ICME'03. Proceedings. 2003 International Conference on, Vol. Vol. 3. IEEE, III--549. Google ScholarDigital Library
- Brian Dickinson and Wei Hu. 2015. Sentiment analysis of investor opinions on twitter. Social Networking, Vol. 4, 03 (2015), 62.Google ScholarCross Ref
- Hans Jurgen Eysenck. 1953. The structure of human personality. (1953).Google Scholar
- Jonathan Gratch and Stacy Marsella. 2001. Tears and fears: Modeling emotions and emotional behaviors in synthetic agents Proceedings of the fifth international conference on Autonomous agents. ACM, 278--285. Google ScholarDigital Library
- L Jean Harrison-Walker. 2001. The measurement of word-of-mouth communication and an investigation of service quality and customer commitment as potential antecedents. Journal of service research Vol. 4, 1 (2001), 60--75.Google ScholarCross Ref
- Jagadeesh Jagarlamudi, Hal Daumé III, and Raghavendra Udupa. 2012. Incorporating lexical priors into topic models. In Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics. Association for Computational Linguistics, 204--213. Google ScholarDigital Library
- Simon Lacoste-Julien, Fei Sha, and Michael I Jordan. 2009. DiscLDA: Discriminative learning for dimensionality reduction and classification Advances in neural information processing systems. 897--904. Google ScholarDigital Library
- Jon D Mcauliffe and David M Blei. 2008. Supervised topic models. In Advances in neural information processing systems. 121--128.Google Scholar
- Keith B Murray. 1991. A test of services marketing theory: consumer information acquisition activities. The journal of marketing (1991), 10--25.Google Scholar
- Richard L Oliver. 1997. Emotional expression in the satisfaction response. Satisfaction: A behavioral perspective on the consumer (1997), 291--325.Google Scholar
- James W Pennebaker, Martha E Francis, and Roger J Booth. 2001. Linguistic inquiry and word count: LIWC 2001. Mahway: Lawrence Erlbaum Associates Vol. 71, 2001 (2001), 2001.Google Scholar
- Rosalind Wright Picard. 1995. Affective computing. (1995).Google Scholar
- Daniel Ramage, David Hall, Ramesh Nallapati, and Christopher D Manning. 2009. Labeled LDA: A supervised topic model for credit attribution in multi-labeled corpora Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 1-Volume 1. Association for Computational Linguistics, 248--256. Google ScholarDigital Library
- Daniel Ramage, Christopher D Manning, and Susan Dumais. 2011. Partially labeled topic models for interpretable text mining Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 457--465. Google ScholarDigital Library
- Timothy N Rubin, America Chambers, Padhraic Smyth, and Mark Steyvers. 2012. Statistical topic models for multi-label document classification. Machine learning, Vol. 88, 1 (2012), 157--208. Google ScholarDigital Library
- Sebastian Schuster and Christopher D Manning. 2016. Enhanced english universal dependencies: An improved representation for natural language understanding tasks. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016).Google Scholar
- Amy K Smith and Ruth N Bolton. 2002. The effect of customers' emotional responses to service failures on their recovery effort evaluations and satisfaction judgments. Journal of the academy of marketing science, Vol. 30, 1 (2002), 5--23.Google ScholarCross Ref
- Maite Taboada, Julian Brooke, Milan Tofiloski, Kimberly Voll, and Manfred Stede. 2011. Lexicon-based methods for sentiment analysis. Computational linguistics Vol. 37, 2 (2011), 267--307. Google ScholarDigital Library
- Mike Thelwall, Kevan Buckley, Georgios Paltoglou, Di Cai, and Arvid Kappas. 2010. Sentiment strength detection in short informal text. Journal of the American Society for Information Science and Technology, Vol. 61, 12 (2010), 2544--2558. Google ScholarDigital Library
- Yang Wang, Payam Sabzmeydani, and Greg Mori. 2007. Semi-latent dirichlet allocation: A hierarchical model for human action recognition. Human Motion--Understanding, Modeling, Capture and Animation (2007), 240--254. Google ScholarDigital Library
- Anbang Xu and Brian Bailey. 2012. A reference-based scoring model for increasing the findability of promising ideas in innovation pipelines. In Proceedings of the ACM 2012 conference on Computer Supported Cooperative Work. ACM, 1183--1186. Google ScholarDigital Library
- Anbang Xu, Zhe Liu, Yufan Guo, Vibha Sinha, and Rama Akkiraju. 2017. A New Chatbot for Customer Service on Social Media Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems (CHI '17). 3506--3510. Google ScholarDigital Library
- Peifeng Yin, Nilam Ram, Wang-Chien Lee, Conrad Tucker, Shashank Khandelwal, and Marcel Salathé. 2014. Two sides of a coin: Separating personal communication and public dissemination accounts in Twitter. In Pacific-Asia Conference on Knowledge Discovery and Data Mining. Springer, 163--175.Google ScholarCross Ref
- Jun Zhu, Amr Ahmed, and Eric P Xing. 2009. MedLDA: maximum margin supervised topic models for regression and classification Proceedings of the 26th annual international conference on machine learning. ACM, 1257--1264. Google ScholarDigital Library
Index Terms
- Tone Analyzer for Online Customer Service: An Unsupervised Model with Interfered Training
Recommendations
Aspect and sentiment unification model for online review analysis
WSDM '11: Proceedings of the fourth ACM international conference on Web search and data miningUser-generated reviews on the Web contain sentiments about detailed aspects of products and services. However, most of the reviews are plain text and thus require much effort to obtain information about relevant details. In this paper, we tackle the ...
LDA Analyzer: A Tool for Exploring Topic Models
ICSME '14: Proceedings of the 2014 IEEE International Conference on Software Maintenance and EvolutionOnline technical forums are valuable sources for mining useful software engineering information. LDA (Latent Dirichlet Allocation) is an unsupervised machine learning method which can be used for extracting underlying topics out of such large forums. ...
Aspect-specific polarity-aware summarization of online reviews
WAIM'13: Proceedings of the 14th international conference on Web-Age Information ManagementWith the popularity of various social media platforms, the number of online reviews towards different products and services grows dramatically. Discovering sentiments from online reviews becomes an important and challenging task in sentiment analysis. ...
Comments