Machine Learning-Based Sentiment Analysis as a Dynamic Early Warning Sign for Financial Distress in Property and Real Estate Companies

Revina Sofia Septiani; Bayu Tri Cahya; Nor ishah Mohd Ali

doi:10.24235/jiesbi.v3i2.593

Authors

Revina Sofia Septiani Universitas Islam Negeri Sunan Kudus, Indonesia Author
Bayu Tri Cahya Universitas Islam Negeri Sunan Kudus, Indonesa Author
Nor ishah Mohd Ali UiTM Melaka, 78000, Malaysia Author

DOI:

https://doi.org/10.24235/jiesbi.v3i2.593

Abstract

This study investigates the integration of sentiment analysis from social media and digital news portals as predictors of financial distress in Indonesian property companies. Intensifying industrial competition in 2024, as reported by KPPU data, has led to shrinking market shares and declining profits. Companies failing to compete face heightened risks of financial distress, necessitating more proactive monitoring tools. Unlike traditional models that rely solely on financial ratios, this research innovates by using investor sentiment as an early warning signal, leveraging advanced crawling techniques such as Tweet Harvest and high-performance analysis in RapidMiner. For the research methods, a total of 1,965 tweets and 602 news articles (2020–2023) were extracted and classified using Naïve Bayes. The relationship between sentiment and financial health (Altman Z-Score) was analyzed using ordinal logistic regression. Results showed that both social media sentiment (p=0.029) and news sentiment (p=0.042) significantly influence financial health. Positive sentiment on platform X shows the strongest predictive power (Exp(B)=3.907) in identifying "healthy" companies. In conclusion, investment sentiment is a robust early warning indicator. Positive investor sentiment significantly reduces the likelihood of financial distress, providing a dynamic, real-time monitoring tool for regulators and investors in a competitive market.

References

Ahdiat, A. (2023). Terseret kasus Meikarta, ini keuangan Lippo Cikarang 5 tahun terakhir. Databoks.https://databoks.katadata.co.id/properti/statistik/cdd26c632c81aa7/terseret-kasus-meikarta-ini-keuangan-lippo-cikarang-5-tahun-terakhir

Al Qamar Ze, A., & Juanda, J. (2023). Pengaruh herding behavior, media, interaksi sosial, dan advocate recommendation terhadap keputusan investasi dengan sentimen investor sebagai variabel intervening. International Journal of Science and Society, 1(2), 1–9.

Algifari. (2000). Analisis Regresi, Teori, Kasus dan Solusi. BPFE-YOGYA.

Arifiana, R., & Khalifaturofi’ah, S. O. (2022). The effect of financial ratios in predicting financial distress in manufacturing companies. Jurnal Riset Bisnis dan Manajemen, 15(2), 103–108. https://doi.org/10.23969/jrbm.v15i2.5838

Basuki, & Prawoto. (2016). Analisis regresi dalam penelitian ekonomi dan bisnis (Dilengkapi dengan aplikasi SPSS & EViews). RajaGrafindo Persada.

Chen, C., & Chen, C.-D. (2020). Financial distress prediction model: The effects of corporate governance indicators. Journal of Forecasting, 39(8), 1238–1252. https://doi.org/https://doi.org/10.1002/for.2684

Dunham, L. M., & Garcia, J. (2021). Measuring the effect of investor sentiment on financial distress. Managerial Finance, 50(12), 1834–1852. https://doi.org/10.1108/MF-02-2021-0056

Pratiwi, E.I, & Imelda, E. (2022). Hubungan kausalitas antara sentimen investor dan pasar keuangan Indonesia. Jurnal Ekonomi, 27(3), 182–201. https://doi.org/10.24912/je.v27i03.872

Erayanti, R. (2019). Pengaruh likuiditas, profitabilitas, dan leverage terhadap prediksi financial distress. Jurnal Riset Akuntansi & Perpajakan (JRAP), 6(1), 38–51. https://doi.org/10.35838/jrap.v6i01.393

Giovanni, A., Utami, D. W., & Yuzevin, T. (2020). Leverage dan profitabilitas dalam memprediksi financial distress perusahaan pertambangan periode 2016–2018. Journal of Business and Banking, 10(1), 151. https://doi.org/10.14414/jbb.v10i1.2292

Griffith, J., Najand, M., & Shen, J. (2020). Emotions in the stock market. Journal of Behavioral Finance, 21(1), 42–56. https://doi.org/10.1080/15427560.2019.1588275

Hidayat, K. (2024). Bumi Serpong (BSDE) profit drops 20.04% in 2023: Check out its stock recommendations. Kontan. https://english.kontan.co.id/news/bumi-serpong-bsde-profit-drops-2004-in-2023-check-out-its-stock-recommendations#:~:text=Bumi Serpong (BSDE) Profit Drops,Check Out Its Stock Recommendations

Komisi Pengawas Persaingan Usaha. (2024). CEDS Unpad : Tingkat persaingan usaha Indonesia tahun 2023 meningkat. https://kppu.go.id/blog/2024/01/ceds-unpad-tingkat-persaingan-usaha-indonesia-tahun-2023-meningkat/

Mahastanti, L. A., & Utami, A. D. (2022). Perbandingan tingkat akurasi model prediksi financial distress pada perusahaan sektor property dan real estate. Accounting and Financial Review, 5(1), 50–63. https://doi.org/10.26905/afr.v5i1.7526

Mengelkamp, A., Wolf, S., & Schumann, M. (2016). Data-driven creation of sentiment dictionaries for corporate credit risk analysis. In Proceedings of the Americas Conference on Information Systems (AMCIS 2016) (pp. 1–9).

News, Indo Premier Securities. (2023). Financial statements full year 2022 of APLN. https://www.indopremier.com/ipotnews/newsDetail.php?jdl=Financial_Statements_Full_Year_2022_of_APLN&news_id=417051&group_news=RESEARCHNEWS&news_date=&taging_subtype=APLN&name=&search=y_general&q=Financial Statements&halaman=1

Nikkinen, J., & Peltomäki, J. (2020). Crash fears and stock market effects: Evidence from web searches and printed news articles. Journal of Behavioral Finance, 21(2), 117–127. https://doi.org/10.1080/15427560.2019.1630125

Pradana, M. G., Nurcahyo, A. C., & Saputro, P. H. (2020). Pengaruh sentimen di sosial media terhadap harga saham perusahaan. Edutic: Scientific Journal of Informatics Education, 6(2), 67–77. https://doi.org/10.21107/edutic.v6i2.6992

Putri, M. A., & Maulana, H. Z. (2023). Memprediksi kebangkrutan menggunakan Altman Z-score pada perusahaan manufaktur sektor makanan dan minuman. Jurnal Cendekia Keuangan, 2(2), 55. https://doi.org/10.32503/jck.v2i2.3431

Qu, S. (2023). A study on the impact of investor sentiment on corporate financial stress based on data mining. In Proceedings of the International Conference on Big Data Economy and Information Management (pp. 845–850). https://doi.org/10.1145/3659211.3659357

Rajan, A. P., & S.P.Victor. (2014). Crawling Twitter data. Journal of Research in Computer Application & Management, 4(9).

Ramadhan, D., & Setiawan, E. B. (2019). Analisis sentimen program acara di SCTV pada Twitter menggunakan metode naive Bayes dan support vector machine. E-Proceeding of Engineering, 6(2), 9736–9743. https://openlibrarypublications.telkomuniversity.ac.id/index.php/engineering/article/view/10708

Resfitasari, E., Taofik Muhammad Gumelar, Andini Ulhaq, & Nina Rusmayanti. (2022). Analisis prediksi financial distress dengan metode Altman Z-score pada PT Waskita Karya Tbk. Jurnal Aktiva: Riset Akuntansi dan Keuangan, 3(3), 131–140. 131–140. https://doi.org/10.52005/aktiva.v3i3.123

Samsir, Irmayani, D., Edi, F., Harahap, J. M., Jupriaman, Rangkuti, R. K., Ulya, B., & Watrianthos, R. (2021). Naive Bayes algorithm for Twitter sentiment analysis. Journal of Physics: Conference Series, 1933(1), 012019. https://doi.org/10.1088/1742-6596/1933/1/012019

Sembiring, S., & Sinaga, H. W. C. (2022). Analisis akurasi model Altman, Grover, Springate, Zmijewski dalam memprediksi kondisi financial distress. Jurnal Riset Akuntansi & Keuangan, 8(2), 299–311. https://doi.org/10.54367/jrak.v8i2.1662

Shiller, R. J. (2017). Narrative economics. American Economic Review, 107(4), 967–1004. https://doi.org/10.1257/aer.107.4.967

Sisbintari, I. (2018). Sekilas tentang behavioral finance. Jurnal Ilmiah Administrasi Bisnis dan Inovasi, 1(2), 88–101. https://doi.org/10.25139/jai.v1i2.814

Sugiyono. (2013). Metode penelitian kuantitatif, kualitatif, dan R&D. Alfabeta.

Sul, H. K., Dennis, A. R., & Yuan, L. I. (2017). Trading on Twitter: Using social media sentiment to predict stock returns. Decision Sciences, 48(3), 454–488. https://doi.org/10.1111/deci.12229

Wongkar, M., & Angdresey, A. (2019). Sentiment analysis using naive Bayes algorithm of the data crawler: Twitter. In Proceedings of the 4th International Conference on Informatics and Computing (ICIC 2019) (pp. 1–5). https://doi.org/10.1109/ICIC47613.2019.8985884

Zhao, S., Xu, K., Wang, Z., Liang, C., Lu, W., & Chen, B. (2022). Financial distress prediction by combining sentiment tone features. Economic Modelling, 106, 105709. https://doi.org/10.1016/j.econmod.2021.105709