Improving Automated Categorization of Customer Requests with Recent Advances in Natural Language Processing

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62156489%3A43110%2F24%3A43926267" target="_blank" >RIV/62156489:43110/24:43926267 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.11118/ejobsat.2024.010" target="_blank" >https://doi.org/10.11118/ejobsat.2024.010</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.11118/ejobsat.2024.010" target="_blank" >10.11118/ejobsat.2024.010</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Improving Automated Categorization of Customer Requests with Recent Advances in Natural Language Processing

Popis výsledku v původním jazyce

In this paper, we focus on the categorization of tickets in service desk systems. We employ modern neural network-based artificial intelligence methods to improve the performance of current systems and address typical problems in the domain. Special attention is paid to balancing the ticket categories, selecting a suitable representation of text data, and choosing a classification model. Based on experiments with two real-world datasets, we conclude that text preprocessing, balancing the ticket categories, and using the representations of texts based on fine-tuned transformers are crucial for building successful classifiers in this domain. Although we could not directly compare our work to other research the results demonstrate superior performance to similar works.

Název v anglickém jazyce

Improving Automated Categorization of Customer Requests with Recent Advances in Natural Language Processing

Popis výsledku anglicky

In this paper, we focus on the categorization of tickets in service desk systems. We employ modern neural network-based artificial intelligence methods to improve the performance of current systems and address typical problems in the domain. Special attention is paid to balancing the ticket categories, selecting a suitable representation of text data, and choosing a classification model. Based on experiments with two real-world datasets, we conclude that text preprocessing, balancing the ticket categories, and using the representations of texts based on fine-tuned transformers are crucial for building successful classifiers in this domain. Although we could not directly compare our work to other research the results demonstrate superior performance to similar works.

Druh

J_SC - Článek v periodiku v databázi SCOPUS

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

European Journal of Business Science and Technology

ISSN

2336-6494

e-ISSN

2694-7161

Svazek periodika

10

Číslo periodika v rámci svazku

2

Stát vydavatele periodika

CZ - Česká republika

Počet stran výsledku

12

Strana od-do

173-184

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-85214573059