Topic Modelling Using Non-Negative Matrix Factorization (NMF) for Telkom University Entry Selection from Instagram Comments

Alfajri Alfajri; Donny Richasdy; Muhammad Arif Bijaksana

doi:10.47065/josyc.v3i4.2212

Alfajri Alfajri * Telkom University, Bandung, Indonesia
Donny Richasdy Telkom University, Bandung, Indonesia
Muhammad Arif Bijaksana Telkom University, Bandung, Indonesia

(*) Corresponding Author

DOI: https://doi.org/10.47065/josyc.v3i4.2212

Keywords: Topic Modelling; Non-negative Matrix Factorization; Instgaram; Topic Coherence; Telkom University

Abstract

The development of information technology is increasingly rapid, such as social media, which has much influence. Social media is a place or media used to express and express various opinions on a topic. One example is Instagram. Instagram is a social media platform with many features, such as posting photos, videos, comments, likes, and others. The comments feature that Instagram has contained much public opinion that can be used as data. Nothing but the post on the SMB Telkom University Instagram account about the entrance to the university. In posts about the entrance to Telkom university, many Instagram users comment on the post. This can be convenient for the marketing team to get topics or discussions that most followers need from Telkom University's Instagram account. Therefore, a topic modelling of Instagram users' perceptions of comments posted on the entrance to Telkom university was carried out using the Nonnegative Matrix Factorization (NMF) method. After doing several research scenarios, the best coherent value was obtained with a coherent value of 0.60628 and the best 4 topics.

Downloads

Download data is not yet available.

References

S. Scholz and C. Winkler, “How to Engage Followers: Classifying Fashion Brands According to Their Instagram Profiles, Posts and Comments,” Dec. 2020, pp. 29–50. doi: 10.5121/csit.2020.101704.

C. B. Asmussen and C. Møller, “Smart literature review: a practical topic modelling approach to exploratory literature review,” J Big Data, vol. 6, no. 1, Dec. 2019, doi: 10.1186/s40537-019-0255-7.

M. Belford, B. mac Namee, and D. Greene, “Stability of topic modeling via matrix factorization,” Expert Syst Appl, vol. 91, pp. 159–169, Jan. 2018, doi: 10.1016/j.eswa.2017.08.047.

E. OKKALI, H. ATAMTÜRK, and Z. H. KİLİMCİ, “Evaluation of Society Response to Violence against Women in Turkey via Twitter using Topic Modeling,” Kocaeli Journal of Science and Engineering, Nov. 2021, doi: 10.34088/kojose.907333.

Z. A. Guven, B. Diri, and T. Cakaloglu, “Comparison Method for Emotion Detection of Twitter Users,” Oct. 2019. doi: 10.1109/ASYU48272.2019.8946435.

ICT International Student Project Conference 3. 2014 Nakhon Pathom, J. L. Mitrpanont, ICT International Student Project Conference 3 2014.03.26-27 Nakhon Pathom, ICT-ISPC 3 2014.03.26-27 Nakhon Pathom, and ISPC 3 2014.03.26-27 Nakhon Pathom, Proceedings of the 2014 Third ICT International Senior Project Conference (ICT-ISPC2014) March 26-27, 2014, Faculty of ICT, Mahidol University, Nakhon Pathom, Thailand. IEEE, 2014.

S. Mifrah, “Topic Modeling Coherence: A Comparative Study between LDA and NMF Models using COVID’19 Corpus,” International Journal of Advanced Trends in Computer Science and Engineering, vol. 9, no. 4, pp. 5756–5761, Aug. 2020, doi: 10.30534/ijatcse/2020/231942020.

M. Chirag and K. Pathela, “Exploring the space of Topic Modelling and Topic Coherence on short and long text corpora,” 2020.

D. O’Callaghan, D. Greene, J. Carthy, and P. Cunningham, “An analysis of the coherence of descriptors in topic modeling,” Expert Syst Appl, vol. 42, no. 13, pp. 5645–5657, Aug. 2015, doi: 10.1016/j.eswa.2015.02.055.

R. Churchill and L. Singh, “textPrep: A Text Preprocessing Toolkit for Topic Modeling on Social Media Data.” [Online]. Available: https://github.com/GU-DataLab/topic-modeling-

A. Oussous, A. A. Lahcen, and S. Belfkih, “Impact of text pre-processing and ensemble learning on Arabic sentiment analysis,” in ACM International Conference Proceeding Series, 2019, vol. Part F148154. doi: 10.1145/3320326.3320399.

R. Churchill and L. Singh, “textPrep: A Text Preprocessing Toolkit for Topic Modeling on Social Media Data,” 2021. [Online]. Available: https://github.com/GU-DataLab/topic-modeling-

E. Zamiraylova and O. Mitrofanova, “Dynamic Topic Modeling of Russian Prose of the First Third of the XXth Century by Means of Non-Negative Matrix Factorization *.”

R. Vangara et al., “Finding the Number of Latent Topics with Semantic Non-negative Matrix Factorization,” IEEE Access, 2021, doi: 10.1109/ACCESS.2021.3106879.

X. Fu, K. Huang, N. D. Sidiropoulos, and W.-K. Ma, “Nonnegative Matrix Factorization for Signal and Data Analytics: Identifiability, Algorithms, and Applications,” Mar. 2018, doi: 10.1109/MSP.2018.2877582.

S. Keputusan Dirjen Penguatan Riset dan Pengembangan Ristek Dikti, Y. Sahria, and D. Hatta Fudholi, “Terakreditasi SINTA Peringkat 2 Analisis Topik Penelitian Kesehatan di Indonesia Menggunakan Metode Topic Modeling LDA (Latent Dirichlet Allocation),” masa berlaku mulai, vol. 1, no. 3, pp. 336–344, 2017.

Zoya, S. Latif, F. Shafait, and R. Latif, “Analyzing LDA and NMF Topic Models for Urdu Tweets via Automatic Labeling,” IEEE Access, vol. 9, pp. 127531–127547, 2021, doi: 10.1109/ACCESS.2021.3112620.

S. Bellaouar, M. M. Bellaouar, and I. E. Ghada, “Topic modeling: Comparison of LSA and LDA on scientific publications,” in ACM International Conference Proceeding Series, Feb. 2021, pp. 59–64. doi: 10.1145/3456146.3456156.

Bila bermanfaat silahkan share artikel ini

Berikan Komentar Anda terhadap artikel Topic Modelling Using Non-Negative Matrix Factorization (NMF) for Telkom University Entry Selection from Instagram Comments