Dina Pisarevskaya
Boris Galitsky
ABSTRACT
Automated detection of text with misrepresentations such as fake reviews is an important task for online reputation management. The dataset of customer complaints - emotionally charged texts which are very similar to reviews and include descriptions of problems customers experienced with certain businesses – is presented. It contains 2746 complaints about banks and provides clear ground truth, based on available factual knowledge about the financial domain. Among them, 400 texts were manually tagged. Initial experiments were performed in order to explore the links between implicit cues of the rhetoric structure of texts and the validity of arguments, and also how truthful/deceptive are these texts.
- Abbott, R., Ecker, B., Anand, P., and Walker, M.A. (2016). “Internet argument corpus 2.0: An sql schema for dialogic social media and the corpora to go with it”. Language Resources and Evaluation Conference.Google Scholar
- Feng, S., Banerjee, R., and Choi, Y. (2012a). “Syntactic stylometry for deception detection”. ACL 12, Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: 171-175. Google ScholarDigital Library
- Feng, S., Xing, L., Gogar, A., and Choi, Y. (2012b). “Distributional footprints of deceptive product reviews”. Sixth International AAAI Conference on Weblogs and Social Media. 98-105.Google Scholar
- Fornaciari, T. and Poesio, M. (2014). “Identifying fake Amazon reviews as learning from crowds”. Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics: 279-287.Google ScholarCross Ref
- Galitsky, B., Ilvovsky, D., and Pisarevskaya, D. (2018). “Argumentation in text: Discourse structure matters”. CICLing 2018 (unpublished).Google Scholar
- Hai, Z., Zhao, P., Cheng, P., Yang, P., Li, X.-L., and Li, G. (2016). “Deceptive review spam detection via exploiting task relatedness and unlabeled data”. Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing: 1817-1826.Google ScholarCross Ref
- Jindal, N. and Liu B. (2008). “Opinion spam and analysis”. Proceedings of International Conference on Web Search and Data Mining (WSDM-2008). Google ScholarDigital Library
- Mann, W.C. and Thompson S.A. (1987). “Rhetorical Structure Theory: Description and Construction of Text Structures”. Springer Netherlands, Dordrecht.Google ScholarCross Ref
- Mukherjee, A., Venkataraman, V., Liu, B., and Glance, N. (2013a). “What Yelp fake review filter might be doing?” Proceedings of the Seventh International AAAI Conference on Weblogs and Social Media.Google Scholar
- Mukherjee, A., Venkataraman, V., Liu, B., and Glance, N. (2013b). “Fake review detection: classification and analysis of real and pseudo reviews”. Tech. rep. uic-cs-2013-03. University of Illinois at Chicago.Google Scholar
- Oraby, S., Reed, L., Compton, R., Riloff, E., Walker, M., and Whittaker, S. (2015). “And that's a fact: Distinguishing factual and emotional argumentation in online dialogue”. NAACL HLT 2015 2nd Workshop on Argumentation Mining.Google ScholarCross Ref
- Ott, M., Cardie, C., and Hancock, J.T. (2013). “Negative deceptive opinion spam”. NAACLHLT 2013, Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: 497-501.Google Scholar
- Ott, M., Choi, Y., Cardie, C., and Hancock, J.T. (2011). “Finding deceptive opinion spam by any stretch of the imagination”. Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Volume 1: 309-319. Google ScholarDigital Library
- Rayana, S. and Akoglu, L. (2015). “Collective opinion spam detection: Bridging review networks and metadata”. Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM: 985-994. Google ScholarDigital Library
- Stab, S. and Gurevych, I. (2017). “Recognizing insufficiently supported arguments in argumentative essays”. Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2017): 980-990.Google ScholarCross Ref
- Sun, C., Du, Q., and Tian, G. (2016). “Exploiting product related review features for fake review detection”. Mathematical Problems in Engineering.Google Scholar
- Yao, W., Dai, Z., Huang, R., and Caverlee, J. (2017). “Online deception detection refueled by real world data collection”. Proceedings of Recent Advances in Natural Language Processing: 793-802.Google Scholar
- Grasso, F. (2003). “Characterizing Rhetoric Argumentation”. PhD Thesis Heriot-Watt University.Google Scholar
- Galitsky, B., Ilvovsky, D., and Makhalova, T. (2019). “Enabling a Bot with Understanding Argumentation and Providing Arguments”. Developing Enterprise Chatbots, Springer Switzerland.Google Scholar
- Joty, S., Carenini, G., Ng, R.T., and Mehdad, Y. (2013). “Combining intra-and multisentential rhetorical parsing for document-level discourse analysis”. ACL (1): 486-496.Google Scholar
- Surdeanu, M., Hicks, T., and Valenzuela-Escarcega, M.A. (2015). “Two Practical Rhetorical Structure Theory Parsers”. NAACL HLT.Google Scholar
- Ganter, B. and Kuznetsov, S.O. (2001). “Pattern Structures and Their Projections”. ICCS, Lecture Notes in Artificial Intelligence (Springer), Vol. 2120: 129-142. Google ScholarDigital Library
- Galitsky, B. (2019). “Rhetorical Agreement: Maintaining Cohesive Conversations”. Developing Enterprise Chatbots, Springer – Cham, Switzerland.Google ScholarCross Ref
- Github (2019). Ultimate Deception Dataset https://github.com/bgalitsky/relevance-based-on-parse-trees/blob/master/examples/ultimateDeceptionAutoTagged.csv.zip.Google Scholar
- Galitsky, B. (2019). “A Content Management System for Chatbots”. Developing Enterprise Chatbots. Springer Switzerland.Google ScholarCross Ref
- Galitsky, B. and Kuznetsov, S.O. (2008). “Learning communicative actions of conflicting human agents”. J. Exp. Theor. Artif. Intell, 20(4): 277–317. Google ScholarDigital Library
- Galitsky, B., Ilvovsky, D., and Kuznetsov, S.O. (2018). “Detecting logical argumentation in text via communicative discourse tree". J. Exp. Theor. Artif. Intell., 30(5): 1-27.Google ScholarCross Ref
Index Terms
- An Anatomy of a Lie:
Recommendations
The Research of Personal Customer Relationship Management for Commercial Banks Based on Multidimensional Model of Customer Loyalty
ICEE '10: Proceedings of the 2010 International Conference on E-Business and E-GovernmentCultivating customer loyalty is a critical goal of customer relationship management (CRM). Traditional CRM is lack of a relatively complete model of customer loyalty and couldn’t support customer loyalty management efficiently in business processes, ...
Organizational Learning Curves for Customer Dissatisfaction: Heterogeneity Across Airlines
In the extensive literature on learning curves, scholars have ignored outcome measures of organizational performance evaluated by customers. We explore whether customer dissatisfaction follows a learning-curve pattern. Do organizations learn to reduce ...
Platform Manipulation in Online Retail Marketplace with Sponsored Advertising
We study an online retail marketplace’s incentive to manipulate sellers’ product attractiveness to consumers (e.g., through fake sales, fake reviews, or dishonest endorsement) and sellers’ placement ranking.
In this paper, we study an online retail marketplace’s incentive to manipulate sellers’ product attractiveness to consumers (e.g., through fake sales, fake reviews, or dishonest endorsement), as well as sellers’ placement ranking. We design a model of an ...
Comments