Intent Identification in Unattended Customer Queries Using an Unsupervised Approach

Hugo D. Rebelo, Lucas A. F. de Oliveira, Gustavo M. Almeida, César A. M. Sotomayor, Geraldo L. Rochocz and Willian E. D. Melo
Additional contact information
Hugo D. Rebelo: Radix – Engineering and Software, Passeio Corporate, R. do Passeio, 38, Tower 2, Centro, Rio de Janeiro 20021-290, RJ, Brazil
Lucas A. F. de Oliveira: #x2020;Radix – Engineering and Software, R. Santa Rita Durão, 444, Funcionários, Belo Horizonte 30140-110, MG, Brazil
Gustavo M. Almeida: #x2021;Department of Chemical Engineering, School of Engineering, Federal University of Minas Gerais, Av. Antonio Carlos, 6627, Pampulha, Belo Horizonte 31270-901, MG, Brazil
César A. M. Sotomayor: Radix – Engineering and Software, Passeio Corporate, R. do Passeio, 38, Tower 2, Centro, Rio de Janeiro 20021-290, RJ, Brazil
Geraldo L. Rochocz: Radix – Engineering and Software, Passeio Corporate, R. do Passeio, 38, Tower 2, Centro, Rio de Janeiro 20021-290, RJ, Brazil
Willian E. D. Melo: #xA7;Cemig Distribution S/A, Av. Barbacena, 1200, Santo Agostinho, Belo Horizonte 30190-924, MG, Brazil

Journal of Information & Knowledge Management (JIKM), 2021, vol. 20, issue 03, 1-26

Abstract: Customer’s satisfaction is crucial for companies worldwide. An integrated strategy composes omnichannel communication systems, in which chabot is widely used. This system is supervised, and the key point is that the required training data are originally unlabelled. Labelling data manually is unfeasible mainly nowadays due to the considerable volume. Moreover, customer behaviour is often hidden in the data even for experts. This work proposes a methodology to find unknown entities and intents automatically using unsupervised learning. This is based on natural language processing (NLP) for text data preparation and on machine learning (ML) for clustering model identification. Several combinations for preprocessing, vectorisation, dimensionality reduction and clustering techniques, were investigated. The case study refers to a Brazilian electric energy company, with a data set of failed customer queries, that is, not met by the company for any reason. They correspond to about 30% (4,044 queries) of the original data set. The best identified intent model employed stemming for preprocessing, word frequency analysis for vectorisation, latent Dirichlet allocation (LDA) for dimensionality reduction, and mini-batch k-means for clustering. This system was able to allocate 62% of the failed queries in one of the seven found intents. For instance, this new labelled data can be used for the training of NLP-based chatbots contributing to a greater generalisation capacity, and ultimately, to increase customer satisfaction.

Keywords: Customer behaviour; customer intent; unsupervised learning; information system; text analytics; ML (search for similar items in EconPapers)
Date: 2021
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.worldscientific.com/doi/abs/10.1142/S0219649221500374
Access to full text is restricted to subscribers

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wsi:jikmxx:v:20:y:2021:i:03:n:s0219649221500374

Ordering information: This journal article can be ordered from

DOI: 10.1142/S0219649221500374

Access Statistics for this article

Journal of Information & Knowledge Management (JIKM) is currently edited by Professor Suliman Hawamdeh

More articles in Journal of Information & Knowledge Management (JIKM) from World Scientific Publishing Co. Pte. Ltd.
Bibliographic data for series maintained by Tai Tone Lim ().