Quantifying chatbots’ ability to learn business processes

Kecht, Christoph; Egger, Andreas; Kratsch, Wolfgang; Röglinger, Maximilian

doi:10.1016/j.is.2023.102176

Cited by 24 publications

(7 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, they may not be able to handle sensitive or confidential information securely, which can pose a risk to customers' privacy and security. Finally, they may lack the ability to learn and improve over time, limiting their effectiveness in meeting evolving customer needs and expectations (Kecht et al, 2023).…”

Section: Existing Chatbots In the Financial Industrymentioning

confidence: 99%

What will ChatGPT revolutionize in the financial industry?

Ali,

Aysan

2023

View full text Add to dashboard Cite

The launch of the open AI chatbot, ChatGPT, in November 2022 has generated widespread excitement around Generative Artificial Intelligence (AI). While researchers have explored ChatGPT's ability to produce content and respond to input, our study takes a different approach and examines its use cases in the financial industry. We aim to understand what ChatGPT offers the financial industry and how it differs from existing banking and financial chatbots. Financial institutions can use ChatGPT for a variety of purposes, including customer engagement, personalization, up-selling and cross-selling, stock forecasting, product development, and financial education. By focusing on the potential of ChatGPT in finance, we hope to spark discussions about its applications in other domains and explore the possibilities of a larger revolution in the future. Finally, this study identifies the challenges associated with the use of Generative Open AI and LLMs-based chatbots in the financial industry and provides recommendations for addressing these challenges.

show abstract

Section: Existing Chatbots In the Financial Industrymentioning

confidence: 99%

What will ChatGPT revolutionize in the financial industry?

Ali,

Aysan

2023

View full text Add to dashboard Cite

show abstract

“…Throughout their experience, clients can communicate with chatbots (Alyahya et al, 2023a;Kecht et al, 2023). By utilizing learning algorithms and predictive modelling, chatbots may instantaneously match a customer's enquiry with accessible products that fulfil their needs (Alyahya et al, 2023b;Brachten et al, 2021).…”

Section: Chatbot Adoptionmentioning

confidence: 99%

Factors Affecting Consumers Adoption of AI-Based Chatbots: The Role of Anthropomorphism

Alboqami¹

2023

AJIBM

View full text Add to dashboard Cite

Previous studies paid more attention to factors affecting consumers intentions and behaviors to adopt IT in the retail industry; however, little attention has been paid to factors affecting consumer intentions to adopt chatbots in the retails industry. This study utilizes technology acceptance models to explore these factors. Quantitative approach method using online survey was adopted to collect data from consumers in Saudi Arabia retail industry. We collected data from 903 consumers and analyzed it using structural equation modeling technique. The findings indicated that perceived intelligence, perceived ease of use, and perceived usefulness have a significant positive influence on consumers intentions to adopt chatbots. It also indicated that technological anxiety has a negative influence on intentions. Our study indicated that anthropomorphism plays a moderating role on these relationships. Our study offers meaningful implications for retailers and marketer to develop their marketing plan and strategy.

show abstract

“…Chatbots are shown to be highly effective to automate frequently requested tasks. Using NLP, they adapt to tasks that are slightly different from their programmed base task (Kecht et al, 2023). Another case (Shaikh et al, 2022) presents a framework with various stages that offers guidelines with enough flexibility to be applicable in complex and heterogeneous corporate environments as well as for small and medium sized companies.…”

Section: Literature Surveymentioning

confidence: 99%

Analyzing and Automating Customer Service Queries on Twitter Using Robotic Process Automation

Kumar¹,

Shidaganti²,

Anand³

et al. 2023

Journal of Computer Science

View full text Add to dashboard Cite

Several product companies have turned to social media to analyze customer satisfaction and provide customer service to disgruntled customers. Product twitter handles are flooded with tweets every day. Customer service professionals struggle to find and resolve complaints from numerous tweets, which results in high wait times for a response, huge costs for the company, and frustrated customers. Automating customer services involves the use of Artificial Intelligence (AI) and Natural Language Processing (NLP) to emulate customer service offered by professionals. Pre-processing and deriving insights from real data are difficult and several start-ups cannot afford funds to maintain a data analysis team. Existing technologies for chatbots and analysis can be improved with new machine learning models, training existing models more and ensuring that responses generated resemble human interactions. BERT-CNN-BiLSTM modules were integrated into a model for sentiment analysis on scraped tweets from twitter using TWINT that achieved an accuracy of 96%. For the labeling and categorization of tweets, the logistic regression linear model achieved the highest accuracy of 97% compared to the other 3 classification models. For the automated chatbot, a model trained with BERT and open AI-GPT achieved an accuracy of 78%.

show abstract

Quantifying chatbots’ ability to learn business processes

Cited by 24 publications

References 49 publications

What will ChatGPT revolutionize in the financial industry?

What will ChatGPT revolutionize in the financial industry?

Factors Affecting Consumers Adoption of AI-Based Chatbots: The Role of Anthropomorphism

Analyzing and Automating Customer Service Queries on Twitter Using Robotic Process Automation

Contact Info

Product

Resources

About