A comparative study of retrieval-based and generative-based chatbots using Deep Learning and Machine Learning
Increased screen time may cause significant health impacts, including harmful effects on mental health. Studies on the association between technological obsessions and their influence on health have been conducted using Deep Learning (DL) and Machine Learning (ML) techniques. The deployment of chatb...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-11-01
|
| Series: | Healthcare Analytics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772442523000655 |
| _version_ | 1797796032708345856 |
|---|---|
| author | Sumit Pandey Srishti Sharma |
| author_facet | Sumit Pandey Srishti Sharma |
| author_sort | Sumit Pandey |
| collection | DOAJ |
| description | Increased screen time may cause significant health impacts, including harmful effects on mental health. Studies on the association between technological obsessions and their influence on health have been conducted using Deep Learning (DL) and Machine Learning (ML) techniques. The deployment of chatbots in different industries has been proven as a game-changer. We study conversational Artificial Intelligence (AI) systems enabling operators to conduct conversations with machines that resemble those with humans. We design and develop two retrieval-based and generative-based chatbots, each with six designs. Among the retrieval-based chatbots, Vanilla Recurrent Neural Network (RNN) has an accuracy of 83.22%, Long Short Term Memory (LSTM) is 89.87% accurate, Bidirectional LSTM (Bi-LSTM) is 91.57% accurate, Gated Recurrent Unit (GRU) is 65.57% accurate, and Convolution Neural Network (CNN) is 82.33% accurate. In comparison, generative-based chatbots have encoder–decoder designs that are 94.45% accurate. The most significant distinction is that while generative-based chatbots can generate new text, retrieval-based chatbots are restricted to responding to inputs that match the best of the outputs they already know. |
| first_indexed | 2024-03-13T03:27:01Z |
| format | Article |
| id | doaj.art-2a9ac91cea394db198df76232a58c88c |
| institution | Directory Open Access Journal |
| issn | 2772-4425 |
| language | English |
| last_indexed | 2024-03-13T03:27:01Z |
| publishDate | 2023-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Healthcare Analytics |
| spelling | doaj.art-2a9ac91cea394db198df76232a58c88c2023-06-25T04:44:22ZengElsevierHealthcare Analytics2772-44252023-11-013100198A comparative study of retrieval-based and generative-based chatbots using Deep Learning and Machine LearningSumit Pandey0Srishti Sharma1Corresponding author.; The NorthCap University School of Engineering & Technology, Gurugram, Haryana, 122017, IndiaThe NorthCap University School of Engineering & Technology, Gurugram, Haryana, 122017, IndiaIncreased screen time may cause significant health impacts, including harmful effects on mental health. Studies on the association between technological obsessions and their influence on health have been conducted using Deep Learning (DL) and Machine Learning (ML) techniques. The deployment of chatbots in different industries has been proven as a game-changer. We study conversational Artificial Intelligence (AI) systems enabling operators to conduct conversations with machines that resemble those with humans. We design and develop two retrieval-based and generative-based chatbots, each with six designs. Among the retrieval-based chatbots, Vanilla Recurrent Neural Network (RNN) has an accuracy of 83.22%, Long Short Term Memory (LSTM) is 89.87% accurate, Bidirectional LSTM (Bi-LSTM) is 91.57% accurate, Gated Recurrent Unit (GRU) is 65.57% accurate, and Convolution Neural Network (CNN) is 82.33% accurate. In comparison, generative-based chatbots have encoder–decoder designs that are 94.45% accurate. The most significant distinction is that while generative-based chatbots can generate new text, retrieval-based chatbots are restricted to responding to inputs that match the best of the outputs they already know.http://www.sciencedirect.com/science/article/pii/S2772442523000655Artificial IntelligenceChatbotDeep LearningMachine LearningMental health |
| spellingShingle | Sumit Pandey Srishti Sharma A comparative study of retrieval-based and generative-based chatbots using Deep Learning and Machine Learning Healthcare Analytics Artificial Intelligence Chatbot Deep Learning Machine Learning Mental health |
| title | A comparative study of retrieval-based and generative-based chatbots using Deep Learning and Machine Learning |
| title_full | A comparative study of retrieval-based and generative-based chatbots using Deep Learning and Machine Learning |
| title_fullStr | A comparative study of retrieval-based and generative-based chatbots using Deep Learning and Machine Learning |
| title_full_unstemmed | A comparative study of retrieval-based and generative-based chatbots using Deep Learning and Machine Learning |
| title_short | A comparative study of retrieval-based and generative-based chatbots using Deep Learning and Machine Learning |
| title_sort | comparative study of retrieval based and generative based chatbots using deep learning and machine learning |
| topic | Artificial Intelligence Chatbot Deep Learning Machine Learning Mental health |
| url | http://www.sciencedirect.com/science/article/pii/S2772442523000655 |
| work_keys_str_mv | AT sumitpandey acomparativestudyofretrievalbasedandgenerativebasedchatbotsusingdeeplearningandmachinelearning AT srishtisharma acomparativestudyofretrievalbasedandgenerativebasedchatbotsusingdeeplearningandmachinelearning AT sumitpandey comparativestudyofretrievalbasedandgenerativebasedchatbotsusingdeeplearningandmachinelearning AT srishtisharma comparativestudyofretrievalbasedandgenerativebasedchatbotsusingdeeplearningandmachinelearning |