View Item 
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Faculty of Mathematics and Natural Sciences
      • UT - Computer Science
      • View Item
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Faculty of Mathematics and Natural Sciences
      • UT - Computer Science
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Analisis Pengalaman Pengguna Terkait Pemanfaatan Large Language Model (LLM) untuk Komunitas Pertanian

      Thumbnail
      View/Open
      Cover (506.8Kb)
      Fulltext (1.424Mb)
      Lampiran (826.0Kb)
      Date
      2024
      Author
      Amalia, Afiqah Nur
      Ardiansyah, Firman
      Asfarian, Auzi
      Metadata
      Show full item record
      Abstract
      Salah satu cara dalam mengatasi tantangan petani dalam mencari informasi secara efisien di internet adalah penggunaan chatbot yang dapat diimplementasi menggunakan Large Language Model (LLM) seperti ChatGPT. Pengalaman yang diberikan LLM dapat memengaruhi pengalaman pengguna yang berkaitan dengan kenyamanan dan kepuasan. Cara untuk menilai sejauh mana peran LLM dalam memberikan pengalaman pengguna yang baik adalah dengan melakukan penelitian menggunakan kuesioner dan wawancara untuk menilai informasi yang diberikan LLM dari aspek kepercayaan, pemahaman, dan gaya komunikasi. Kuesioner dibuat berdasarkan wawancara kepada petani dan penyuluh pertanian serta jawaban dari ChatGPT dan dosen pertanian yang dibagikan kepada 11 petani di Kecamatan Dramaga. Sebanyak 6 responden di antaranya diwawancara untuk menjelaskan hasil kuantitatif. Hasilnya, jawaban dari dosen lebih unggul dalam segala aspek. Meskipun demikian, rata-rata respon positif setiap jawaban LLM bernilai cukup tinggi. Akan tetapi, masih ada beberapa kekurangan informasi dari LLM seperti panjang informasi dan penggunaan kata-kata yang dianggap masih asing oleh responden.
       
      One way to overcome farmers' challenges in finding information efficiently on the internet is using chatbot that can be implemented using Large Language Model (LLM) such as ChatGPT. The experience provided by the LLM can influence the user experience in terms of comfort and satisfaction. The way to assess the extent of the LLM's role in providing a good user experience is to conduct research using questionnaires and interviews to assess the information provided by the LLM in terms of trust, understanding, and communication style. The questionnaire was made based on interviews with farmers and agricultural extension workers, also responses from ChatGPT and agricultural lecturers, and was distributed to 11 farmers in Dramaga District. A total of 6 respondents were interviewed to explain the quantitative results. The results showed that the responses from the lecturers were superior in all aspects. Nevertheless, the average positive response of each LLM response was quite high. However, there were still some shortcomings in the information provided by the LLM, such as the length of information and the use of unfamiliar words for respondents.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/157312
      Collections
      • UT - Computer Science [2482]

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository
        

       

      Browse

      All of IPB RepositoryCollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

      My Account

      Login

      Application

      google store

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository