Optimizing Contextual Features for Instagram Engagement Prediction using Long Short-Term Memory (LSTM)
-
Hazrul Aswad
*
STIKOM Cipta Karya Informatika, DKI Jakarta,
Indonesia
- Dadang Iskandar Mulyana STIKOM Cipta Karya Informatika, DKI Jakarta, Indonesia
- Kastum Kastum STIKOM Cipta Karya Informatika, DKI Jakarta, Indonesia (*) Corresponding Author
Abstract
Instagram has become an important communication medium for academic institutions, enabling the dissemination of information, promotion of activities, and engagement with the campus community. At STIKOM CKI Jakarta, the official Instagram account plays a key role in academic communication, making it essential to optimize content strategies for higher audience interaction. This study analyzes 311 publicly available posts collected from July 2023 to July 2025 from the institution’s official account. Although relatively small for deep learning, the dataset provides representative patterns for the case study while highlighting the model’s capability under limited data conditions. A predictive framework based on Long Short-Term Memory (LSTM) was developed by integrating textual features from captions with contextual features such as posting time, content type, hashtag count, and interaction metrics. The aim is to accurately estimate engagement scores and provide actionable posting recommendations. The evaluation achieved an R² of 88.00%, MAE of 0.0450, and RMSE of 0.0720, indicating strong predictive performance. The contribution of this research lies in demonstrating that optimizing contextual features can significantly enhance academic social media engagement and in providing an adaptable methodology for institutions with limited historical data.
Downloads
References
Abdalrdha, Z. K., Al-Bakry, A. M., & Farhan, A. K. (2023). A Hybrid CNN-LSTM and XGBoost Approach for Crime Detection in Tweets Using an Intelligent Dictionary. Revue d’Intelligence Artificielle, 37 (6)(6), 1651–1661. https://doi.org/10.18280/RIA.370630
Akarsh, S., Sriram, S., Poornachandran, P., Menon, V. K., & Soman, K. P. (2019). Deep Learning Framework for Domain Generation Algorithms Prediction Using Long Short-term Memory. 2019 5th International Conference on Advanced Computing and Communication Systems, ICACCS 2019, 666–671. https://doi.org/10.1109/ICACCS.2019.8728544
Alhayan, F., Pennington, D. R., & Ayouni, S. (2018). Measuring Passive Engagement with Health Information on Social Media. IEEE. https://doi.org/10.1109/NCG.2018.8593032
Amira Sumitro, P., Rasiban, Iskandar Mulyana, D., & Saputro, W. (2021). Analisis Sentimen Terhadapat Vaksin Covid-19 di Indonesia pada Twitter Menggunakan Metode Lexicon Based. J-ICOM, 2 (2), 50–56. https://doi.org/10.33059/j-icom.v2i2.4009
Barnes, S., & Rutter, R. (2020). Using Big Data and AI to Examine Product Engagement in Social Media Influencer Posts. https://doi.org/10.1109/ICITISEE48480.2019.9003991
Celuch, K. (2021). Hashtag usage and user engagement on instagram: The case of #foodfestivals. Journal of Physical Education and Sport, 21, 966–973. https://doi.org/10.7752/jpes.2021.s2120
Chen, N., & Wang, P. (2019). Advance Combined LSTM-CNN Model for Twitter Sentiment Analysis. Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/CCIS.2018.8691381
Duan, Y., Lv, Y., & Wang, F.-Y. (2016). Travel Time Prediction with LSTM Neural Network. IEEE. https://doi.org/10.1109/ITSC.2016.7795686
Halbouni, A., Gunawan, T. S., Habaebi, M. H., Halbouni, M., Kartiwi, M., & Ahmad, R. (2022). CNN-LSTM: Hybrid Deep Neural Network for Network Intrusion Detection System. IEEE, 10(1), 99837–999849. https://doi.org/10.1109/ACCESS.2022.3206425
Hariss, P., Gojal, J., Chitra, R., & Anithra, S. (2021). Fake Instagram Profile Identification and Classification using Machine Learning (Vol. 9, Issue 4). https://doi.org/10.1109/GCAT52182.2021.9587858
Islam, M. Z., Islam, M. M., & Asraf, A. (2020). A combined deep CNN-LSTM network for the detection of novel coronavirus (COVID-19) using X-ray images. Informatics in Medicine Unlocked, 20. https://doi.org/10.1016/j.imu.2020.100412.
Istiake Sunny, M. A., Maswood, M. M. S., & Alharbi, A. G. (2020). Deep Learning-Based Stock Price Prediction Using LSTM and Bi-Directional LSTM Model. 2nd Novel Intelligent and Leading Emerging Sciences Conference, NILES 2020, 87–92. https://doi.org/10.1109/NILES50944.2020.9257950
Khoeri, I., & Mulyana, I. D. (2021). Implementasi Machine Learning dengan Decision Tree Algoritma C4.5 dalam Penerimaan Karyawan Baru pada PT. Gitareksa Dinamika Jakarta. SOSTECH, 1 (7), 616–623. https://doi.org/10.59188/jurnalsostech.v1i7.126
Kong, Y., Zhou, T., Liang, Y., Sun, P., Wang, Z., Nie, Y., Zohren, S., & Wen, Q. (2024). Unlocking the Power of LSTM for Long Term Time Series Forecasting. https://doi.org/https://doi.org/10.48550/arXiv.2408.10006
Landi, F., Baraldi, L., Cornia, M., & Cucchiara, R. (2021). Working Memory Connections for LSTM. Neural Networks, 144, 334–341. https://doi.org/10.1016/j.neunet.2021.08.030
Malhotra, A., & Jindal, R. (2020). Multimodal deep learning based framework for detecting depression and suicidal behaviour by affective analysis of social media posts. EAI Endorsed Transactions on Pervasive Health and Technology, 6 (1), 1–9. https://doi.org/10.4108/eai.13-7-2018.164259
Moharm, K., Eltahan, M., & Elsaadany, E. (2020). Wind speed forecast using LSTM and Bi-LSTM algorithms over gabal el-zayt wind farm. Proceedings - 2020 International Conference on Smart Grids and Energy Systems, SGES 2020, 922–927. https://doi.org/10.1109/SGES51519.2020.00169
Mutegeki, R., & Han, D. S. (2020). A CNN-LSTM Approach to Human Activity Recognition. IEEE. https://doi.org/10.1109/ICAIIC48513.2020.9065078
Nurhambali, M. R., Angraini, Y., & Fitrianto, A. (2024). Implementation of Long Short-Term Memory for Gold Prices Forecasting. Malaysian Journal of Mathematical Sciences, 18 (2), 399–422. https://doi.org/10.47836/mjms.18.2.11
Prajapati, J. B., & Patel, S. K. (2021). Performance Comparison of Machine Learning Algorithms for Prediction of Students’ Social Engagement. Proceedings - 5th International Conference on Computing Methodologies and Communication, ICCMC 2021, 947–951. https://doi.org/10.1109/ICCMC51019.2021.9418260
Priadana, A., Maarif, M. R., & Habibi, M. (2021). Gender Prediction for Instagram User Profiling using Deep Learning. 2020 International Conference on Decision Aid Sciences and Application, DASA 2020, 432–436. https://doi.org/10.1109/DASA51403.2020.9317143
Purba, K. R., Asirvatham, D., & Murugesan, R. K. (2021). Instagram post popularity trend analysis and prediction using hashtag, image assessment, and user history features. International Arab Journal of Information Technology, 18 (1), 85–94. https://doi.org/10.34028/iajit/18/1/10
Sahib, M. R., Elkina, H., & Zaki, T. (2024). From Technical Indicators to Trading Decisions: A Deep Learning Model Combining CNN and LSTM. International Journal of Advanced Computer Science and Applications, 15 (6)(6), 847–855. https://doi.org/10.14569/IJACSA.2024.0150685
Salim, F., & Wahyudhy, A. I. (2025). Klasifikasi Berita Palsu Menggunakan Pendekatan Hybrid CNN-LSTM Fake News Classification Using Hybrid CNN-LSTM Approach. 6 (1), 55–59. https://doi.org/10.37859/coscitech.v6i1.8615
Satpathy, R., Choudhury, T., & Satpathy, S. (2021). Forecasting of Novel Corona Virus Disease (Covid-19) Using LSTM and XG Boosting Algorithms. https://doi.org/10.1002/9781119785620.ch12
Venkatesh, Hegde, S. U., Zaiba, A. S., & Nagaraju, Y. (2021, April 6). Hybrid CNN-LSTM model with glove word vector for sentiment analysis on football specific tweets. Proceedings of the 2021 1st International Conference on Advances in Electrical, Computing, Communications and Sustainable Technologies, ICAECT 2021. https://doi.org/10.1109/ICAECT49130.2021.9392516
Wijayanti, A. Y. (2022). Analisis User Engagement pada Akun Instagram Perpustakaan di Masa Covid-19. Jurnal Pustaka Ilmiah, 8 (2), 48–54. https://doi.org/10.20961/jpi.v8i2.62061
Wu, J. M. T., Wu, M. E., Hung, P. J., Hassan, M. M., & Fortino, G. (2020). Convert index trading to option strategies via LSTM architecture. Neural Computing and Applications. https://doi.org/10.1007/s00521-020-05377-6
Zhang, P., Ouyang, W., Zhang, P., Xue, J., & Zheng, N. (2019). SR-LSTM: State refinement for lstm towards pedestrian trajectory prediction. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2019-June, 12077–12086. https://doi.org/10.1109/CVPR.2019.01236
Zhang, Z., Chen, T., Zhou, Z., & Li, J. (2019). How to Become Instagram Famous: Post Popularity Prediction with Dual-Attention. IEEE. https://doi.org/10.1109/BigData.2018.8622461
Zhou, X. (2021). Stock Price Prediction using Combined LSTM-CNN Model. Proceedings - 2021 3rd International Conference on Machine Learning, Big Data and Business Intelligence, MLBDBI 2021, 67–71. https://doi.org/10.1109/MLBDBI54094.2021.00020
Zohourian, A., Sajedi, H., & Yavary, A. (2018a). Popularity Prediction of Images and Videos on Instagram. IEEE. https://doi.org/10.1109/ICWR.2018.8387246
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Optimizing Contextual Features for Instagram Engagement Prediction using Long Short-Term Memory (LSTM)
Pages: 303-311
Copyright (c) 2025 Hazrul Aswad, Dadang Iskandar Mulyana, Kastum Kastum
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
