Empowering geoportals HCI with task-oriented chatbots through NLP and deep transfer learning
In the past ten years, chatbot development has matured to become one of the most well-distinguished outcomes of artificial intelligence. Despite some criticism, Bing AI, ChatGPT and other natural language processing (NLP) products of similar nature are becoming more popular. The creation of chatbots...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2024-10-01
|
| Series: | Big Earth Data |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/20964471.2024.2403166 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850052051783909376 |
|---|---|
| author | Mohammad H. Vahidnia |
| author_facet | Mohammad H. Vahidnia |
| author_sort | Mohammad H. Vahidnia |
| collection | DOAJ |
| description | In the past ten years, chatbot development has matured to become one of the most well-distinguished outcomes of artificial intelligence. Despite some criticism, Bing AI, ChatGPT and other natural language processing (NLP) products of similar nature are becoming more popular. The creation of chatbots can close several gaps in geographic information retrieval as well. This research introduces and successfully implements, for the first time, a model for integrating task-oriented chatbots into geoportals, with the goal of easing user requests, improving access to geospatial services, and fostering human-computer interactions (HCI). Additionally, it presents a novel recommendation solution for matching the most appropriate volunteer to the user’s geospatial needs based on expertise similarity, semantic similarity, and community feedback. The three categories of finding map services, discovering geoprocessing services, and volunteer expert recommendations were shown to be the most significant geoportal bot intents. Depending on the requirement, each intent additionally includes various entities such as time, place, description, skill, etc. The notion of deep transfer learning (DTL) was then put into practice by customizing a pre-trained BERT (Bidirectional Encoder Representations from Transformers) model for our particular aim and creating a task-oriented conversational agent. According to the results, effective intent classification and entity recognition in the geospatial domain could arise from this approach. We performed the training process with 200 sample data, 20% of which were utilized in a stratified manner for testing, and we obtained f1-scores of at least 0.75. Finally, a pilot Geoportal Chabot that combines crowdsourcing and conversational agents’ approaches was put into use and tested with success. In keeping with SDI technical purposes, the system might direct users to common geospatial web services, namely WMS and WPS, in addition to including natural language understanding (NLU) and natural language generation (NLG) capabilities. Result of user-centered evaluation indicated that the integration of a chatbot significantly reduces the average time required to access geospatial data and processing services by more than 50%. Notably, this effect is even more pronounced when locating an expert, with a fivefold decrease in the time required. Finally, overall user satisfaction rose from 86% to 94%. |
| format | Article |
| id | doaj-art-95077dfee82644c7bd7cfd6835cb07c7 |
| institution | DOAJ |
| issn | 2096-4471 2574-5417 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Big Earth Data |
| spelling | doaj-art-95077dfee82644c7bd7cfd6835cb07c72025-08-20T02:52:56ZengTaylor & Francis GroupBig Earth Data2096-44712574-54172024-10-018460864810.1080/20964471.2024.2403166Empowering geoportals HCI with task-oriented chatbots through NLP and deep transfer learningMohammad H. Vahidnia0Center for Remote Sensing and GIS Research, Faculty of Earth Sciences, Shahid Beheshti University, Tehran, IranIn the past ten years, chatbot development has matured to become one of the most well-distinguished outcomes of artificial intelligence. Despite some criticism, Bing AI, ChatGPT and other natural language processing (NLP) products of similar nature are becoming more popular. The creation of chatbots can close several gaps in geographic information retrieval as well. This research introduces and successfully implements, for the first time, a model for integrating task-oriented chatbots into geoportals, with the goal of easing user requests, improving access to geospatial services, and fostering human-computer interactions (HCI). Additionally, it presents a novel recommendation solution for matching the most appropriate volunteer to the user’s geospatial needs based on expertise similarity, semantic similarity, and community feedback. The three categories of finding map services, discovering geoprocessing services, and volunteer expert recommendations were shown to be the most significant geoportal bot intents. Depending on the requirement, each intent additionally includes various entities such as time, place, description, skill, etc. The notion of deep transfer learning (DTL) was then put into practice by customizing a pre-trained BERT (Bidirectional Encoder Representations from Transformers) model for our particular aim and creating a task-oriented conversational agent. According to the results, effective intent classification and entity recognition in the geospatial domain could arise from this approach. We performed the training process with 200 sample data, 20% of which were utilized in a stratified manner for testing, and we obtained f1-scores of at least 0.75. Finally, a pilot Geoportal Chabot that combines crowdsourcing and conversational agents’ approaches was put into use and tested with success. In keeping with SDI technical purposes, the system might direct users to common geospatial web services, namely WMS and WPS, in addition to including natural language understanding (NLU) and natural language generation (NLG) capabilities. Result of user-centered evaluation indicated that the integration of a chatbot significantly reduces the average time required to access geospatial data and processing services by more than 50%. Notably, this effect is even more pronounced when locating an expert, with a fivefold decrease in the time required. Finally, overall user satisfaction rose from 86% to 94%.https://www.tandfonline.com/doi/10.1080/20964471.2024.2403166Conversational agentvolunteered geographic information (VGI)expert recommendationdeep learningtoponym |
| spellingShingle | Mohammad H. Vahidnia Empowering geoportals HCI with task-oriented chatbots through NLP and deep transfer learning Big Earth Data Conversational agent volunteered geographic information (VGI) expert recommendation deep learning toponym |
| title | Empowering geoportals HCI with task-oriented chatbots through NLP and deep transfer learning |
| title_full | Empowering geoportals HCI with task-oriented chatbots through NLP and deep transfer learning |
| title_fullStr | Empowering geoportals HCI with task-oriented chatbots through NLP and deep transfer learning |
| title_full_unstemmed | Empowering geoportals HCI with task-oriented chatbots through NLP and deep transfer learning |
| title_short | Empowering geoportals HCI with task-oriented chatbots through NLP and deep transfer learning |
| title_sort | empowering geoportals hci with task oriented chatbots through nlp and deep transfer learning |
| topic | Conversational agent volunteered geographic information (VGI) expert recommendation deep learning toponym |
| url | https://www.tandfonline.com/doi/10.1080/20964471.2024.2403166 |
| work_keys_str_mv | AT mohammadhvahidnia empoweringgeoportalshciwithtaskorientedchatbotsthroughnlpanddeeptransferlearning |