Bitte verwenden Sie diesen Link, um diese Publikation zu zitieren, oder auf sie als Internetquelle zu verweisen: http://hdl.handle.net/10419/237440
Erscheinungsjahr: 
2021
Quellenangabe: 
[Journal:] CBN Journal of Applied Statistics [ISSN:] 2476-8472 [Volume:] 12 [Issue:] 1 [Publisher:] The Central Bank of Nigeria [Place:] Abuja [Year:] 2021 [Pages:] 77-108
Verlag: 
The Central Bank of Nigeria, Abuja
Zusammenfassung: 
This paper analyses textual data mined from 37,460 reviews written by mobile banking application users in Nigeria over the period November 2012 - July 2020. On a scale of 1 to 5 (5 being the best), the average user rating for the twenty-two apps included in our sample is 3.5; with the apps deployed by non-interest banks having the highest average rating of 4.0 and those by commercial banks with national authorisation having the least rating of 3.4. Results from the sentiment analysis reveal that the share of positive sentiment words (17.8%) in the corpus more than double that of negative sentiment words (7.7%). Furthermore, we find that about 66 per cent of the emotions expressed by the users are associated with "trust", "anticipation", and "joy" while the remaining 34 per cent relate to "surprise", "fear", "anger", and "disgust". These results imply that majority of the users are satisfied with their mobile banking experience. Finally, we find that the main topics contained in the user reviews pertain to (i) feedback on banks' responsiveness to user complaints (ii) user experience regarding app functionalities and updates, and (iii) operational failures associated with the use of the apps. These results highlight the need for banks to continue to promote awareness of existing functionalities on their apps, educate users on how those solutions could be accessed, and respond to user feedback in a timely and effective manner.
Schlagwörter: 
Mobile banking
sentiment analysis
text mining
JEL: 
C46
C55
D14
D18
E44
E58
G20
Persistent Identifier der Erstveröffentlichung: 
Dokumentart: 
Article

Datei(en):
Datei
Größe
428.1 kB





Publikationen in EconStor sind urheberrechtlich geschützt.