Use of Twitter Data Toward the Development of an English and Swahili Question Answering Agent for the Kenyan Customer Service Market

Kwizera, Felix; Markus, Isaac; Mugambi, Purity; Diriye, Abdigani

doi:10.1145/3136560.3136587

Cited by 2 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dunphy [ 11 ] sampled 698 tweets with the hashtag “#password” and then performed Qualitative Content Analysis to identify themes and then label tweets into higher-level categories. Kwizera [ 23 ] developed an automated chatbot system for the Kenyan Customer Service Market. Fichet [ 13 ] examined how back and forth conversations on Twitter aided in crisis relief.…”

Section: Related Workmentioning

confidence: 99%

Understanding mobile money grievances from tweets

Shah

Mare

Anderson

2019

Proceedings of the Tenth International Conference on Information and Communication Technologies and Development

View full text Add to dashboard Cite

Access to financial services through a mobile phone, known as Mobile Financial Services (MFS), creates an opportunity to expand the reach of financial services to the 1.7 billion unbanked adults worldwide. Nevertheless, MFS adoption has been inconsistent, which motivates a need to identify the challenges that MFS users confront in different countries. In this work, we explore the Twitter as a potential data source to understand such challenges. More broadly, we assess whether (and how) publicly available Twitter data can augment the findings of expensive, large-scale research studies on MFS barriers. Our Qualitative Content Analysis of 9,000 mobile money grievance tweets that were extracted from 54 MFS customer care twitter feeds across six countries reveals service and access issues, incorrect transactions, and fraud as three main challenges MFS users report on Twitter. We discuss the nuances around these challenges and the substantial differences between the common issues reported in different countries. Ultimately, we conclude that Twitter data can elucidate the challenges of MFS adoption and also that it can augment the results of other types of MFS studies.

show abstract

Section: Related Workmentioning

confidence: 99%

Understanding mobile money grievances from tweets

Shah

Mare

Anderson

2019

Proceedings of the Tenth International Conference on Information and Communication Technologies and Development

View full text Add to dashboard Cite

show abstract

Intrance: Designing an Interactive Enhancement System for the Development of QA Chatbots

Feine

Morana

Maedche

2022

Proc. ACM Hum.-Comput. Interact.

View full text Add to dashboard Cite

User input is essential for the successful development of question-and-answer (QA) chatbots. Therefore, interactive development systems are emerging that allow developers to involve test-users in the QA chatbot development process. Although the feasibility and effectiveness of this approach have been demonstrated, there is a lack of knowledge on how to design interactive QA chatbot development systems to increase test-user engagement as well as data quality in this time-consuming and tedious task. To address this research gap, we propose an interactive system design based on the interactivity effects model. We instantiate the proposed design and introduce Intrance, an interactive enhancement system for QA chatbots. Subsequently, we show in two online experiments that the proposed design significantly increases subjective and objective engagement of test-users and has a positive effect on data quality, conceptualized as data completeness and data accuracy. We discuss design implications for an implementation of the proposed design in commercial chatbot development systems.

show abstract

Use of Twitter Data Toward the Development of an English and Swahili Question Answering Agent for the Kenyan Customer Service Market

Cited by 2 publications

References 7 publications

Understanding mobile money grievances from tweets

Understanding mobile money grievances from tweets

Intrance: Designing an Interactive Enhancement System for the Development of QA Chatbots

Contact Info

Product

Resources

About