A comparative study of retrieval-based and generative-based chatbots using Deep Learning and Machine Learning

Pandey, Sumit; Sharma, Srishti

doi:10.1016/j.health.2023.100198

Cited by 21 publications

(4 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, several challenges hinder the development and deployment of such chatbots. Firstly, ensuring that chatbots produce responses that are contextually appropriate and logically coherent remains a significant challenge [24]. Generative-based models, while offering potential for creativity, often struggle with maintaining logical consistency.…”

Section: Methodsmentioning

confidence: 99%

Retrieval based Emotionally responsive chatbot Utilizing emotions clustering and XAI Techniques.

Ashen

2024

Preprint

View full text Add to dashboard Cite

Chatbots are becoming increasingly prevalent in our daily lives, handling a variety of tasks from booking flights to checking the balance of a bank account. However, these interactions are often limited to transactional nature, lacking the depth and nuance of natural human conversations. Therefore, while chatbots are becoming more sophisticated, they still have a significant way to go in terms of authentic human-like interaction. Enhancing chatbots' ability to interact with humans and making them more user-friendly is a crucial challenge in contemporary conversational technology. One promising approach is to imbue these chatbots with the ability to express and understand emotions. Hence, the focus is on developing empathetic dialogue systems that effectively model empathy, ultimately making chatbots more human-like in their interactions with users. In this project, A retrieval-based approach is adopted to mitigate the limitations encountered in generative-based models, particularly concerning logical coherence and response appropriateness. Unlike generative models, retrieval-based approaches offer a more pragmatic solution that demands fewer computational resources. Through the integration of deep learning techniques, transparency in decision-making processes is ensured by eXplainable Artificial Intelligence (XAI), providing users with insights into the chatbot's reasoning. Furthermore, clustering techniques are leveraged to generalize various emotion types, allowing the chatbot to cater to a broader spectrum of emotional inputs effectively.

show abstract

Section: Methodsmentioning

confidence: 99%

Retrieval based Emotionally responsive chatbot Utilizing emotions clustering and XAI Techniques.

Ashen

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…DMHI solutions present the opportunity to create novel and easily accessible mental health therapies, such as telepsychiatry and online counseling, and mental health chatbots. The utilization of technology can also involve the collection and analysis of vast amounts of data, which can offer insights into the occurrence and potential causes of mental health disorders, as well as the effectiveness of various treatments (Pandey & Sharma, 2023).…”

Section: Digital Mental Health Interventionsmentioning

confidence: 99%

Revolutionizing Peer Support for Children with Chronic Illness Leveraging Technology

Gyamlani

2023

PSYCH

View full text Add to dashboard Cite

Children with chronic health conditions face an increased risk for mental health issues compared to their healthy peers. These mental health conditions can negatively impact disease management and medical outcomes. Digital mental health interventions (DMHIs), such as computerized Cognitive Behavioral Therapy and conversational AI, may help address this need. This paper describes an in-progress DMHI using generative AI called Starfly. Starfly connects children with chronic illness with peers to facilitate positive interactions without stigma. The app offers a secure platform for social support and community building among young people managing chronic illness. By leveraging AI and thoughtful design, Starfly aims to promote mental well-being and improve disease outcomes in this vulnerable population.

show abstract

“…Although ELIZA's capabilities were relatively limited, it paved the way for later, more advanced chatbots that can facilitate realistic dialogues with users (Godwin-Jones 2023). Over time, chatbot models have continued to evolve, leading to the current classification of these tools into two primary categories: retrieval-based and generative-based chatbots (Pandey and Sharma 2023). The retrieval-based chatbots function by selecting replies from a predefined database of conversation snippets (Han et al 2021).…”

Section: Chatbots and Ai-enhanced Language Learning Toolsmentioning

confidence: 99%

ChatGPT and L2 Written Communication: A Game-Changer or Just Another Tool?

Zadorozhnyy,

Lai

2023

Languages

View full text Add to dashboard Cite

The development of English language written communication skills across many contexts has been hindered by factors such as examination-oriented cultures, anxiety associated with both oral and written communication, limited opportunities for engaging in authentic communication, and a lack of individualized, personalized feedback. Multiple studies throughout the last decade have explored chatbot integration as a means to address these issues and enhance students’ language learning toolkits. This paper delves into the potential benefits and roles of advanced Generative AI (GenAI) chatbots (e.g., ChatGPT) in enhancing second language (L2) communicative practices. We evaluate findings associated with various types of chatbots and present pedagogical strategies for their application of GenAI in both in-class and out-of-class spaces to support students’ language learning experiences. We also propose future research directions, emphasizing the necessity to explore the ethical use of AI tools, their impact on L2 communication, and the comparative effectiveness of retrieval-based and GenAI-powered chatbots in language education.

show abstract

A comparative study of retrieval-based and generative-based chatbots using Deep Learning and Machine Learning

Cited by 21 publications

References 29 publications

Retrieval based Emotionally responsive chatbot Utilizing emotions clustering and XAI Techniques.

Retrieval based Emotionally responsive chatbot Utilizing emotions clustering and XAI Techniques.

Revolutionizing Peer Support for Children with Chronic Illness Leveraging Technology

ChatGPT and L2 Written Communication: A Game-Changer or Just Another Tool?

Contact Info

Product

Resources

About