TY - JOUR
T1 - Modelling taxpayers’ behaviour based on prediction of trust using sentiment analysis
AU - Coita, Ioana Florina
AU - Belbe, Stefana (Ștefana)
AU - Mare, Codruta (Codruța)
AU - Osterrieder, Joerg
AU - Hopp, Christian
N1 - Funding Information:
This paper is part of the project COST CA19130 FinAI - Fintech and Artificial Intelligence in Finance - Towards a Transparent Financial Industry, and was supported by an STSM and a VMG grant from this COST Action. We also acknowledge the support of COST Action CA21163, the Swiss National Science Foundation (SNSF IZCNZ0-174853, SNSF IZSEZ0-211195, SNSF IZCOZ0-213370), Horizon 2020 ICT-35-2018 and MSCA Doctoral Network 101119635. Lastly, we acknowledge the cooperative relationship between the ING Group and the University of Twente. Our findings are our own and do not necessarily represent the views of the supporting institutions.
Publisher Copyright:
© 2023
PY - 2023/12
Y1 - 2023/12
N2 - Fiscal systems depend on taxpayer's behaviour in terms of their willingness to comply or engage in fraud, deeply rooted in trustworthiness. To gain insights into taxpayers' perceptions and their influence on trust within taxation system, we use survey data to analyse word frequencies, sentiments, attitudes. Our approach utilizes natural language processing in conjunction with machine learning techniques. We highlight a notable correlation: taxpayers who lack trust in fiscal system tend to employ a higher frequency of negative words and exhibit limited word diversity in their expressions. The presence of negative sentiments may potentially foster fraudulent behaviours in the future.
AB - Fiscal systems depend on taxpayer's behaviour in terms of their willingness to comply or engage in fraud, deeply rooted in trustworthiness. To gain insights into taxpayers' perceptions and their influence on trust within taxation system, we use survey data to analyse word frequencies, sentiments, attitudes. Our approach utilizes natural language processing in conjunction with machine learning techniques. We highlight a notable correlation: taxpayers who lack trust in fiscal system tend to employ a higher frequency of negative words and exhibit limited word diversity in their expressions. The presence of negative sentiments may potentially foster fraudulent behaviours in the future.
KW - Behavioural modelling
KW - Sentiment analysis
KW - Taxpayers’ behaviour
KW - Theory of planned behaviour (TPB)
KW - 2023 OA procedure
UR - https://www.scopus.com/pages/publications/85173159766
U2 - 10.1016/j.frl.2023.104549
DO - 10.1016/j.frl.2023.104549
M3 - Article
AN - SCOPUS:85173159766
SN - 1544-6123
VL - 58
JO - Finance Research Letters
JF - Finance Research Letters
IS - Part C
M1 - 104549
ER -