Melola Discovery

← Melola Discovery

Open access Jurnal SINTA 3

Chatbot WhatsApp Asisten Workout dengan Integrasi Large Language Model Gemini dan spaCy

SemanTIK: Teknik Informasi · Vol. 11 No. 1 (2025)

DOI
10.55679/semantik.v11i1.111
ISSN
2502-8928, 2460-1446
Published
2025-06-19
Publisher
Informatics Engineering Department of Halu Oleo University
Language
eng
License
creativecommons.org/licenses/by-sa/4.0

Abstract

Olahraga memiliki peran penting dalam meningkatkan kesehatan fisik dan mental serta mencegah risiko penyakit kronis. Namun, berdasarkan laporan World Health Organization (WHO) tahun 2022 menunjukkan bahwa sekitar 1,4 miliar orang dewasa di dunia masih mengalami kurangnya aktivitas fisik, yang meningkatkan risiko penyakit kronis. Penelitian ini bertujuan mengembangkan chatbot asistensi olahraga untuk membantu individu menjaga rutinitas olahraga yang konsisten. Metode pengembangan sistem menggunakan Software Development Life Cycle (SDLC) model iterative incremental, sedangkan Natural Language Processing (NLP) berbasis spaCy digunakan sebagai metode pemrosesan teks untuk memahami input pengguna. Selain itu, chatbot diintegrasikan dengan API Large Language Model (LLM) Gemini untuk menghasilkan respons berdasarkan basis pengetahuan chatbot. Hasil evaluasi menunjukkan kinerja chatbot yang baik, dengan akurasi 79%, presisi 85%, recall 79%, dan F1-score 77%. Pengujian black-box mencatat tingkat keberhasilan 91,67% dari 12 skenario. Dari hasil tersebut, dapat disimpulkan bahwa chatbot asistensi olahraga ini efektif dalam mendukung pola hidup sehat dan dapat menjadi pendekatan teknologi untuk membantu meningkatkan aktivitas fisik secara mandiri Exercise plays an important role in improving both physical and mental health while also preventing the risk of chronic diseases. However, according to the 2022 World Health Organization (WHO) report, approximately 1.4 billion adults worldwide still experience physical inactivity, which increases the risk of chronic diseases. This research aims to develop an exercise assistance chatbot to help individuals maintain a consistent workout routine. The system development process follows the Software Development Life Cycle (SDLC) iterative incremental model, while Natural Language Processing (NLP) using spaCy is employed for text processing to understand user input. Additionally, the chatbot is integrated with Gemini’s Large Language Model (LLM) API to generate responses based on its knowledge base. Evaluation results indicate good chatbot performance, with an accuracy of 79%, precision of 85%, recall of 79%, and an F1-score of 77%. Black-box testing recorded a 91.67% success rate across 12 test scenarios. These results suggest that the exercise assistance chatbot is effective in promoting a healthy lifestyle and serves as a technological solution to encourage independent physical activity.

Keywords

Collaboration network of the authors

8 authors · 12 co-authorship links

Hover or tap a name to highlight its co-authors. Double-click to open the author's page.

  • Universitas Muhammadiyah Sidoarjo
  • Different organisations
  • Same organisation
  • Affiliation unknown
  • Thicker line = more joint articles · bigger circle = more articles
Show as table
Co-authorOrganisationJoint articles
Mahelda Asri SudarsonoUniversitas Muhammadiyah Sidoarjo1
Yulian FindawatiUniversitas Muhammadiyah Sidoarjo1
Uce IndahyantiUniversitas Muhammadiyah Sidoarjo1
Azmuri Wahyu AzinarUniversitas Muhammadiyah Sidoarjo1
Yoga Mahendra PutraUniversitas Muhammadiyah Sidoarjo1

Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.

Metadata source: OAI-PMH (metadata jurnal) https://semantik.uho.ac.id/index.php/journal/oai, first harvested 26 Okt 2026, last seen 26 Okt 2026.
Original metadata (oai_dc) 
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en-US">Chatbot WhatsApp Asisten Workout dengan Integrasi Large Language Model Gemini dan spaCy</dc:title>
	<dc:creator>Khuzaini, M. Aris</dc:creator>
	<dc:creator>Astutik, Ika Ratna Indra</dc:creator>
	<dc:creator>Fitrani, Arif Senja</dc:creator>
	<dc:subject xml:lang="en-US">Olahraga</dc:subject>
	<dc:subject xml:lang="en-US">Chatbot</dc:subject>
	<dc:subject xml:lang="en-US">Natural Language Processing</dc:subject>
	<dc:subject xml:lang="en-US">Gemini AI</dc:subject>
	<dc:description xml:lang="en-US">Olahraga memiliki peran penting dalam meningkatkan kesehatan fisik dan mental serta mencegah risiko penyakit kronis. Namun, berdasarkan laporan World Health Organization (WHO) tahun 2022 menunjukkan bahwa sekitar 1,4 miliar orang dewasa di dunia masih mengalami kurangnya aktivitas fisik, yang meningkatkan risiko penyakit kronis. Penelitian ini bertujuan mengembangkan chatbot asistensi olahraga untuk membantu individu menjaga rutinitas olahraga yang konsisten. Metode pengembangan sistem menggunakan Software Development Life Cycle (SDLC) model iterative incremental, sedangkan Natural Language Processing (NLP) berbasis spaCy digunakan sebagai metode pemrosesan teks untuk memahami input pengguna. Selain itu, chatbot diintegrasikan dengan API Large Language Model (LLM) Gemini untuk menghasilkan respons berdasarkan basis pengetahuan chatbot. Hasil evaluasi menunjukkan kinerja chatbot yang baik, dengan akurasi 79%, presisi 85%, recall 79%, dan F1-score 77%. Pengujian black-box mencatat tingkat keberhasilan 91,67% dari 12 skenario. Dari hasil tersebut, dapat disimpulkan bahwa chatbot asistensi olahraga ini efektif dalam mendukung pola hidup sehat dan dapat menjadi pendekatan teknologi untuk membantu meningkatkan aktivitas fisik secara mandiri
Exercise plays an important role in improving both physical and mental health while also preventing the risk of chronic diseases. However, according to the 2022 World Health Organization (WHO) report, approximately 1.4 billion adults worldwide still experience physical inactivity, which increases the risk of chronic diseases. This research aims to develop an exercise assistance chatbot to help individuals maintain a consistent workout routine. The system development process follows the Software Development Life Cycle (SDLC) iterative incremental model, while Natural Language Processing (NLP) using spaCy is employed for text processing to understand user input. Additionally, the chatbot is integrated with Gemini’s Large Language Model (LLM) API to generate responses based on its knowledge base. Evaluation results indicate good chatbot performance, with an accuracy of 79%, precision of 85%, recall of 79%, and an F1-score of 77%. Black-box testing recorded a 91.67% success rate across 12 test scenarios. These results suggest that the exercise assistance chatbot is effective in promoting a healthy lifestyle and serves as a technological solution to encourage independent physical activity.</dc:description>
	<dc:publisher xml:lang="en-US">Informatics Engineering Department of Halu Oleo University</dc:publisher>
	<dc:date>2025-06-19</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en-US">Peer-reviewed Article</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://semantik.uho.ac.id/index.php/journal/article/view/111</dc:identifier>
	<dc:identifier>10.55679/semantik.v11i1.111</dc:identifier>
	<dc:source xml:lang="en-US">SemanTIK : Teknik Informasi; Vol. 11 No. 1 (2025): Vol. 11 No. 1 (2025): SemanTIK Teknik Informasi</dc:source>
	<dc:source>2502-8928</dc:source>
	<dc:source>2460-1446</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://semantik.uho.ac.id/index.php/journal/article/view/111/21</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2025 M. Aris Khuzaini, Ika Ratna Indra Astutik, Arif Senja Fitrani</dc:rights>
	<dc:rights xml:lang="en-US">https://creativecommons.org/licenses/by-sa/4.0</dc:rights>
</oai_dc:dc>