Tinjauan Literatur Sistematis terhadap Text-to-SQL Berbasis Model Bahasa Besar untuk Akses Basis Data pada Analitik Olahraga
DOI:
https://doi.org/10.52436/1.jpti.2188Kata Kunci:
akses basis data bahasa alami, large language models, sports analytics, systematic literature review, text-to-SQLAbstrak
Analitik olahraga berkembang dari analisis statistik deskriptif menuju sistem berbasis kecerdasan buatan yang mendukung pemantauan performa, prediksi hasil, dan pengambilan keputusan strategis. Namun, akses terhadap data olahraga yang tersimpan dalam basis data relasional masih menjadi tantangan bagi pengguna non-teknis karena membutuhkan pemahaman struktur basis data dan query SQL. Penelitian ini menyajikan Systematic Literature Review (SLR) mengenai Large Language Models (LLMs) untuk Natural Language Database Access dalam Sports Analytics Systems. Kajian ini menggunakan protokol PRISMA dengan basis data Scopus sebagai sumber utama. Dari 239 artikel awal, diperoleh 65 artikel Scopus yang layak dianalisis dan 1 artikel tambahan sebagai pendukung. Hasil kajian menunjukkan adanya peningkatan tren publikasi pada periode 2020-2026, dengan jumlah tertinggi pada tahun 2025. Area studi paling dominan adalah Sports Analytics, diikuti Natural Language Database Access, Healthcare/Wearable Analytics, Business Analytics, dan Urban/Environmental Analytics. Literatur yang dikaji menunjukkan relevansi Text-to-SQL, Speech-to-SQL, LLM, wearable sensor, dan query generation dalam mendukung akses serta analisis data olahraga. Meskipun demikian, masih terdapat tantangan berupa generalisasi model, kompleksitas skema basis data, interpretabilitas, integrasi data multimodal, privasi data atlet, dan bias algoritma. Arah pengembangan selanjutnya diarahkan pada arsitektur berbasis LLM-agent yang mengintegrasikan intent routing, safety guards, query builder, dan AI response generation untuk mendukung akses bahasa alami terhadap data sports analytics. Penelitian ini memiliki keterbatasan pada aspek teknis karena proses pencarian literatur hanya dilakukan melalui satu basis data utama, yaitu Scopus. Akibatnya, terdapat kemungkinan bahwa sejumlah publikasi yang relevan dan terindeks pada basis data lain belum terakomodasi dalam analisis.
Unduhan
Referensi
B. S. Baumer, G. J. Matthews, and Q. Nguyen, “Big ideas in sports analytics and statistical tools for their investigation,” WIREs Computational Stats, vol. 15, no. 6, p. e1612, Nov. 2023, doi: 10.1002/wics.1612.
Y. F. Roumani, “Sports analytics in the NFL: classifying the winner of the superbowl,” Ann Oper Res, vol. 325, no. 1, pp. 715–730, Jun. 2023, doi: 10.1007/s10479-022-05063-x.
L. Shi, Z. Tang, N. Zhang, X. Zhang, and Z. Yang, “A Survey on Employing Large Language Models for Text-to-SQL Tasks,” ACM Comput. Surv., vol. 58, no. 2, pp. 1–37, Jan. 2026, doi: 10.1145/3737873.
M. Liu, X. Wang, J. Xu, W. Yi, and O. Wolfson, “A systematic review of natural language interfaces for databases,” Front. Comput. Sci., vol. 20, no. 11, p. 2011623, Nov. 2026, doi: 10.1007/s11704-025-50592-w.
B. G. Ascoli, Y. S. R. Kandikonda, and J. D. Choi, “ETM: Modern Insights into Perspective on Text-to-SQL Evaluation in the Age of Large Language Models,” Future Internet, vol. 17, no. 8, p. 325, Jul. 2025, doi: 10.3390/fi17080325.
L. B. Baker et al., “Skin-interfaced microfluidic system with personalized sweating rate and sweat chloride analytics for sports science applications,” Sci. Adv., vol. 6, no. 50, p. eabe3929, Dec. 2020, doi: 10.1126/sciadv.abe3929.
N. M. Watanabe, S. Shapiro, and J. Drayer, “Big Data and Analytics in Sport Management,” Journal of Sport Management, vol. 35, no. 3, pp. 197–202, May 2021, doi: 10.1123/jsm.2021-0067.
Y. Song, R. C.-W. Wong, and X. Zhao, “Speech-to-SQL: toward speech-driven SQL query generation from natural language question,” The VLDB Journal, vol. 33, no. 4, pp. 1179–1201, Jul. 2024, doi: 10.1007/s00778-024-00837-0.
P. Pietraszewski et al., “The Role of Artificial Intelligence in Sports Analytics: A Systematic Review and Meta-Analysis of Performance Trends,” Applied Sciences, vol. 15, no. 13, p. 7254, Jun. 2025, doi: 10.3390/app15137254.
E. R. Nascimento et al., “A Text-to-SQL strategy based on large language models and knowledge graphs for real-world databases,” Data & Knowledge Engineering, vol. 164, p. 102580, Jul. 2026, doi: 10.1016/j.datak.2026.102580.
I. Ghosh, S. Ramasamy Ramamurthy, A. Chakma, and N. Roy, “Sports analytics review: Artificial intelligence applications, emerging technologies, and algorithmic perspective,” WIREs Data Min & Knowl, vol. 13, no. 5, p. e1496, Sep. 2023, doi: 10.1002/widm.1496.
T. Zhao, J. Cabral, and G. Zhu, “A novel explainable artificial intelligence framework using knockoffs techniques with applications to sports analytics,” Ann Oper Res, Apr. 2025, doi: 10.1007/s10479-025-06575-y.
B. G. Ascoli and J. D. Choi, “Advancing Conversational Text-to-SQL: Context Strategies and Model Integration with Large Language Models,” Future Internet, vol. 17, no. 11, p. 527, Nov. 2025, doi: 10.3390/fi17110527.
F. Zhou et al., “Nabil: A Text-to-SQL Model Based on Brain-Inspired Computing Techniques and Large Language Modeling,” Electronics, vol. 14, no. 19, p. 3910, Sep. 2025, doi: 10.3390/electronics14193910.
Z. Pu et al., “Orientation and Decision-Making for Soccer Based on Sports Analytics and AI: A Systematic Review,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 1, pp. 37–57, Jan. 2024, doi: 10.1109/JAS.2023.123807.
C. Russo, C. Tommasino, and A. M. Rinaldi, “Leveraging Graphs for Advanced Analytics in Major Team Sports: A Systematic Mapping Study,” ACM Comput. Surv., vol. 58, no. 6, pp. 1–35, Apr. 2026, doi: 10.1145/3773024.
A. Usta, A. Karakayali, and Ö. Ulusoy, “xDBTagger: explainable natural language interface to databases using keyword mappings and schema graph,” The VLDB Journal, vol. 33, no. 2, pp. 301–321, Mar. 2024, doi: 10.1007/s00778-023-00809-w.
M. Kang and S. Lee, “Is Sport Analytics a Saving Boat for Traditional Measurement and Evaluation in Kinesiology?,” Measurement in Physical Education and Exercise Science, pp. 1–12, Dec. 2025, doi: 10.1080/1091367X.2025.2600451.
S. Acharja and K. Chowdhury, “Natural Language Interfaces for Spatial and Temporal Databases: A Comprehensive Overview of Methods, Taxonomy, and Future Directions,” IEEE Access, vol. 14, pp. 66971–66992, 2026, doi: 10.1109/ACCESS.2026.3686352.
M. Kovoor, M. Durairaj, M. S. Karyakarte, M. Zair Hussain, M. Ashraf, and L. P. Maguluri, “Sensor-enhanced wearables and automated analytics for injury prevention in sports,” Measurement: Sensors, vol. 32, p. 101054, Apr. 2024, doi: 10.1016/j.measen.2024.101054.
Z. Zhan, E. Haihong, and M. Song, “Leveraging Large Language Model for Enhanced Text-to-SQL Parsing,” IEEE Access, vol. 13, pp. 30497–30504, 2025, doi: 10.1109/ACCESS.2025.3540072.
A. Alzahrani and A. Ullah, “Advanced biomechanical analytics: Wearable technologies for precision health monitoring in sports performance,” DIGITAL HEALTH, vol. 10, p. 20552076241256745, Jan. 2024, doi: 10.1177/20552076241256745.
D. Liu and W. Wang, “Advancing sports performance evaluation through T spherical fuzzy FUCA MCDM approach to real time basketball analytics,” Sci Rep, vol. 16, no. 1, p. 3119, Jan. 2026, doi: 10.1038/s41598-025-32934-7.
J. Davis et al., “Methodology and evaluation in sports analytics: challenges, approaches, and lessons learned,” Mach Learn, vol. 113, no. 9, pp. 6977–7010, Sep. 2024, doi: 10.1007/s10994-024-06585-0.
K. Ahkouk and M. Machkour, “Towards an interface for translating natural language questions to SQL: a conceptual framework from a systematic review,” IJRIS, vol. 12, no. 4, p. 264, 2020, doi: 10.1504/IJRIS.2020.111786.
J. Seelhöfer, J. Wick, and M. Witt, “Towards Continuous Swim Leg Analytics in Olympic Triathlon: A Systematic Review of Sensor-Based Assessment Approaches in Open-Water Sports Contexts,” Sensors, vol. 26, no. 7, p. 2151, Mar. 2026, doi: 10.3390/s26072151.
M. Liu, X. Wang, J. Xu, H. Lu, and Y. Tong, “NALSpatial: A Natural Language Interface for Spatial Databases,” IEEE Trans. Knowl. Data Eng., vol. 37, no. 4, pp. 2056–2070, Apr. 2025, doi: 10.1109/TKDE.2025.3525587.
S. Zhou and M. Zhu, “Enhancing Athlete Performance Using Deep Learning Techniques in Sports Analytics,” IEEE Access, vol. 13, pp. 210758–210771, 2025, doi: 10.1109/ACCESS.2025.3631851.
H. S. Shalaan, T. H. A. Soliman, and A. M. AbdelAziz, “G-SQL: A Schema-Aware and Rule-Guided Approach for Robust Natural Language to SQL Translation,” IEEE Access, vol. 13, pp. 158520–158534, 2025, doi: 10.1109/ACCESS.2025.3607879.
Y. Gui, “Enhancing Physical Education Analytics: An Analytic Hierarchy Process-Based Approach for College Sport,” IEEE Access, vol. 13, pp. 40317–40330, 2025, doi: 10.1109/ACCESS.2025.3542557.
C. Yu et al., “Monkuu: a LLM-powered natural language interface for geospatial databases with dynamic schema mapping,” International Journal of Geographical Information Science, vol. 40, no. 2, pp. 588–609, Feb. 2026, doi: 10.1080/13658816.2025.2533322.
H. M. Pandey, A. Gupta, S. Sarkar, M. Tomer, S. Johannes, and Y. Gong, “GEMMA-SQL: A Novel Text-to-SQL Model Based on Large Language Models,” Applied Artificial Intelligence, vol. 39, no. 1, p. 2587371, Dec. 2025, doi: 10.1080/08839514.2025.2587371.
A. Augustine, G. P. Redding, and S. L. Moan, “Toward Explainable Data and Sports Analytics: A Case Study on Pass Completion Prediction in American Football,” The American Statistician, vol. 79, no. 4, pp. 435–448, Oct. 2025, doi: 10.1080/00031305.2025.2541085.
Á. Becsei et al., “A case study using sewage metagenomic data for assessment of text-to-SQL capabilities in large language models,” Sci Rep, vol. 15, no. 1, p. 44557, Nov. 2025, doi: 10.1038/s41598-025-28341-7.
V. Sarlis, G. Papageorgiou, and C. Tjortjis, “Sports Analytics for Evaluating Injury Impact on NBA Performance,” Information, vol. 16, no. 8, p. 699, Aug. 2025, doi: 10.3390/info16080699.
H. Gong, “An approach for enhancing physical education analytics for college sports using AHP based MCDM algorithm integrated with MEREC method,” Sci Rep, vol. 15, no. 1, p. 37034, Oct. 2025, doi: 10.1038/s41598-025-20626-1.
R. Zhou and F. Zhang, “Refining Zero-Shot Text-to-SQL Benchmarks via Prompt Strategies with Large Language Models,” Applied Sciences, vol. 15, no. 10, p. 5306, May 2025, doi: 10.3390/app15105306.
S. Ojuri, T. A. Han, R. Chiong, and A. Di Stefano, “Optimizing text-to-SQL conversion techniques through the integration of intelligent agents and large language models,” Information Processing & Management, vol. 62, no. 5, p. 104136, Sep. 2025, doi: 10.1016/j.ipm.2025.104136.
D. C. M?nescu, “Big Data Analytics Framework for Decision-Making in Sports Performance Optimization,” Data, vol. 10, no. 7, p. 116, Jul. 2025, doi: 10.3390/data10070116.
G. Jiang, W. Li, C. Yu, Z. Zhu, and W. Li, “FGCSQL: A Three-Stage Pipeline for Large Language Model-Driven Chinese Text-to-SQL,” Electronics, vol. 14, no. 6, p. 1214, Mar. 2025, doi: 10.3390/electronics14061214.
Q. Zhang, Z. Wang, C. Long, and S.-M. Yiu, “Billiards Sports Analytics: Datasets and Tasks,” ACM Trans. Knowl. Discov. Data, vol. 18, no. 9, pp. 1–27, Nov. 2024, doi: 10.1145/3686804.
V. Sarlis and C. Tjortjis, “Sports Analytics: Data Mining to Uncover NBA Player Position, Age, and Injury Impact on Performance and Economics,” Information, vol. 15, no. 4, p. 242, Apr. 2024, doi: 10.3390/info15040242.
J.-D. Kim and K. Okubo, “Customizing GPT for natural language dialogue interface in database access,” Genom. Inform., vol. 22, no. 1, p. 22, Nov. 2024, doi: 10.1186/s44342-024-00020-5.
S. K. Thisani, “Developing a High-Performance Sports Results Prediction Artificial Neural Network: Case Study on World Championship Boxing,” International Journal of Computer Science in Sport, vol. 23, no. 2, pp. 1–21, Jun. 2024, doi: 10.2478/ijcss-2023-0008.
V. Sarlis, G. Papageorgiou, and C. Tjortjis, “Leveraging Sports Analytics and Association Rule Mining to Uncover Recovery and Economic Impacts in NBA Basketball,” Data, vol. 9, no. 7, p. 83, Jun. 2024, doi: 10.3390/data9070083.
A. Marshan, A. N. Almutairi, A. Ioannou, D. Bell, A. Monaghan, and M. Arzoky, “MedT5SQL: a transformers-based large language model for text-to-SQL conversion in the healthcare domain,” Front. Big Data, vol. 7, p. 1371680, Jun. 2024, doi: 10.3389/fdata.2024.1371680.
J. Exel and P. Dabnichki, “Precision Sports Science: What Is Next for Data Analytics for Athlete Performance and Well-Being Optimization?,” Applied Sciences, vol. 14, no. 8, p. 3361, Apr. 2024, doi: 10.3390/app14083361.
R. Liu, T. Lu, S. Yuan, H. Zhou, and M. Gowda, “SmartDampener: An Open Source Platform for Sport Analytics in Tennis,” Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., vol. 8, no. 3, pp. 1–30, Aug. 2024, doi: 10.1145/3678507.
S. Swamidorai, T. S. Murthy, and K. V. Sriharsha, “Translating natural language questions to SQL queries (nested queries),” Multimed Tools Appl, vol. 83, no. 15, pp. 45391–45405, Oct. 2023, doi: 10.1007/s11042-023-16987-2.
V. Sarlis, G. Papageorgiou, and C. Tjortjis, “Sports Analytics and Text Mining NBA Data to Assess Recovery from Injuries and Their Economic Impact,” Computers, vol. 12, no. 12, p. 261, Dec. 2023, doi: 10.3390/computers12120261.
O. Olaniyan, B. Dehe, D. Bamford, and S. Ward, “Enhancing on-pitch learning capabilities with data analytics and technologies in elite sports,” European Sport Management Quarterly, vol. 24, no. 6, pp. 1195–1214, Nov. 2024, doi: 10.1080/16184742.2023.2270565.
M. Muniz and T. Flamand, “Sports analytics for balanced team-building decisions,” Journal of the Operational Research Society, vol. 74, no. 8, pp. 1892–1909, Aug. 2023, doi: 10.1080/01605682.2022.2118634.
Y. Özgüven, U. Gönener, and S. Eken, “A Dockerized big data architecture for sports analytics,” ComSIS, vol. 19, no. 2, pp. 957–978, 2022, doi: 10.2298/CSIS220118010O.
M. S. Fury, L. S. Oh, and E. M. Berkson, “New Opportunities in Assessing Return to Performance in the Elite Athlete: Unifying Sports Medicine, Data Analytics, and Sports Science,” Arthroscopy, Sports Medicine, and Rehabil., vol. 4, no. 5, Oct. 2022, doi: 10.1016/j.asmr.2022.08.001.
J. Wu, D. Liu, Z. Guo, Q. Xu, and Y. Wu, “TacticFlow: Visual Analytics of Ever-Changing Tactics in Racket Sports,” IEEE Trans. Visual. Comput. Graphics, vol. 28, no. 1, pp. 835–845, Jan. 2022, doi: 10.1109/TVCG.2021.3114832.
J. Wang et al., “Tac-Trainer: A Visual Analytics System for IoT-based Racket Sports Training,” IEEE Trans. Visual. Comput. Graphics, pp. 1–11, 2022, doi: 10.1109/TVCG.2022.3209352.
X. Ma, X. Liu, X. Li, and Y. Ma, “Light-Weight, Self-Powered Sensor Based on Triboelectric Nanogenerator for Big Data Analytics in Sports,” Electronics, vol. 10, no. 19, p. 2322, Sep. 2021, doi: 10.3390/electronics10192322.
K. C. Houtmeyers, A. Jaspers, and P. Figueiredo, “Managing the Training Process in Elite Sports: From Descriptive to Prescriptive Data Analytics,” International Journal of Sports Physiology and Performance, vol. 16, no. 11, pp. 1719–1723, Nov. 2021, doi: 10.1123/ijspp.2020-0958.
L. Morra, F. Manigrasso, and F. Lamberti, “SoccER: Computer graphics meets sports analytics for soccer event recognition,” SoftwareX, vol. 12, p. 100612, Jul. 2020, doi: 10.1016/j.softx.2020.100612.
S. Ye, S. Feng, L. Huang, and S. Bian, “Recent Progress in Wearable Biosensors: From Healthcare Monitoring to Sports Analytics,” Biosensors, vol. 10, no. 12, p. 205, Dec. 2020, doi: 10.3390/bios10120205.
A. Solanki and A. Kumar, “A system to transform natural language queries into SQL queries,” Int. j. inf. tecnol., vol. 14, no. 1, pp. 437–446, Feb. 2022, doi: 10.1007/s41870-018-0095-2.
G. Durán, “Sports scheduling and other topics in sports analytics: a survey with special reference to Latin America,” TOP, vol. 29, no. 1, pp. 125–155, Apr. 2021, doi: 10.1007/s11750-020-00576-9.
X. Su, Y. Gu, P. Wang, W. Gu, L. Qi, and J. He, “A robust natural language text-to-SQL generation framework with dynamic strategies based on LLMs,” Sci Rep, vol. 16, no. 1, p. 7892, Feb. 2026, doi: 10.1038/s41598-026-39128-9.
M. S. E. D. L. Parte, Y. Wang, J.-F. Martínez-Ortega, and N. L. Martínez, “A Secure and Efficient LLM-Based System for Natural Language Query-to-SQL Translation in IoT Data Management,” IEEE Access, vol. 14, pp. 28435–28456, 2026, doi: 10.1109/ACCESS.2026.3665980.
A. Spelta, “An unbalanced optimal transport framework for histogram-valued regression with applications to sports analytics,” J Big Data, vol. 13, no. 1, p. 51, Feb. 2026, doi: 10.1186/s40537-026-01388-7.
