A text mining and topic modeling based bibliometric exploration of information science research

Silwattananusarn, Tipawan; Kulkanjanapiban, Pachisa

doi:10.11591/ijai.v11.i3.pp1057-1065

Cited by 4 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Moreover, it allows researchers to contextualize their own work within the broader landscape of their discipline and highlight how their work addresses critical questions or contributes to existing knowledge gaps [8], [9]. Building upon the work of others and integrating relevant findings into one's own research is a common practice for researchers [6], [10], [11]. Accurate topic identification in scientific articles facilitates efficient literature reviews, enabling researchers to swiftly locate relevant papers and stay up to date with the latest findings and developments, ultimately saving valuable time.…”

Section: Introductionmentioning

confidence: 99%

Topic Modeling for Scientific Articles: Exploring Optimal Hyperparameter Tuning in BERT

Wijanto,

Widiastuti,

Yong

2024

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

Topic modeling has emerged as a successful approach to uncovering topics from textual data. Various topic modeling techniques have been introduced, ranging from traditional algorithms to those based on neural networks. In this research, we explore advanced topic modeling techniques, including BERT-based approaches, to enhance the analysis of scientific articles. We first investigate a widely used Latent Dirichlet Allocation (LDA) model and then explore the capabilities of BERT, to automatically uncover latent topics within scientific papers. The goal of this study is to identify the optimal hyperparameter setting for BERT-based topic modeling of scientific articles. We conduct experiments across several scenarios involving combinations of word embedding, dimension reduction, and clustering methods. The results were analyzed based on the coherence values, average execution time, number of topics generated, visualization through the inter-topic distance map, and the top-N-words of each topic. Our findings suggest that combination of RoBERTa for word embedding, PCA for dimension reduction, and K-Means for clustering yields superior results among the tested scenarios. Further evaluation of BERT-based topic modeling is necessary to validate these findings and explore its applications in various academic and industrial contexts. The implications of these advanced techniques could significantly streamline the process of staying updated with scientific literature, potentially revolutionizing research methodologies across disciplines.

show abstract

Section: Introductionmentioning

confidence: 99%

Topic Modeling for Scientific Articles: Exploring Optimal Hyperparameter Tuning in BERT

Wijanto,

Widiastuti,

Yong

2024

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

show abstract

“…Melalui penggunaan algoritma dan metode analisis bahasa alami yang canggih, Text Mining mampu secara otomatis mengevaluasi pola dan tren yang muncul dalam teks-teks yang dianalisis, termasuk literatur, dokumen, dan data teks lainnya. Dengan demikian, teknologi ini memungkinkan pengguna untuk mendapatkan pemahaman konten yang lebih mendalam dan komprehensif daripada sekadar menganalisis jumlah kata dasar [5].…”

unclassified

Perbandingan Naïve Bayes dan CNN yang Dioptimasi PSO pada Identifikasi Berita Hoax Politik Indonesia

Kurnia,

Kusuma,

Kusuma

et al. 2024

bit-Tech

View full text Add to dashboard Cite

Berita palsu dalam politik menjadi ancaman serius terhadap stabilitas demokrasi dan kepercayaan publik terhadap informasi. Fenomena ini tidak hanya meresahkan, tetapi juga memiliki dampak yang dapat mengganggu proses demokrasi serta kepercayaan masyarakat terhadap media dan pemerintah. Penelitian ini bertujuan untuk menyelidiki dan membandingkan kinerja dua algoritma yang berbeda, yaitu Naïve Bayes (NB) dan Convolutional Neural Network (CNN), yang telah dioptimalkan menggunakan Particle Swarm Optimization (PSO), dalam mendeteksi berita palsu di ranah politik Indonesia. Untuk mencapai tujuan ini, penelitian menggunakan dataset berita politik yang telah melalui proses text preprocessing, termasuk pembersihan data dan normalisasi teks. Hasil penelitian menunjukkan bahwa model Naïve Bayes secara konsisten mampu mengungguli kinerja CNN, baik dengan atau tanpa penerapan PSO. Akurasi model Naïve Bayes mencapai 90.71%, sementara CNN mencapai 80.86% tanpa PSO, 79.68% dengan PSO, dan Naïve Bayes dengan PSO mencapai 90.25%. Temuan ini menegaskan bahwa pendekatan menggunakan algoritma Naïve Bayes memiliki potensi lebih besar dalam mengidentifikasi berita palsu dalam konteks politik Indonesia. Kontribusi signifikan dari penelitian ini terletak pada pemahaman yang lebih mendalam mengenai metode deteksi berita palsu, serta memberikan wawasan yang penting bagi pengembangan strategi yang efektif dalam menanggulangi permasalahan berita palsu di era digital. Oleh karena itu, diharapkan bahwa penelitian ini akan memberikan nilai tambah dalam upaya mempertahankan keaslian informasi politik dan meningkatkan kualitas demokrasi di Indonesia.

show abstract

“…Meanwhile, information visualization technology for bibliometric analysis is VOSviewer [12][13][14] and Biblioshiny [15, [16]. Many researchers in various fields use bibliometric analysis, such as in the areas of supply chain management [17,18], blockchain technology [19], urban planning and development [20], text mining [21], environmental, social, and governance [22,23], economy [24], machine learning [25], IoT [26], and municipal waste management [27].…”

mentioning

confidence: 99%

Current Trend, Future Direction, and Enablers of e-Waste Management: Bibliometric Analysis and Literature Review

Soesanto¹,

Maarif²,

Anwar³

et al. 2023

Pol. J. Environ. Stud.

View full text Add to dashboard Cite

In terms of preserving and protecting the environment, the ability to recycle metals from e-waste is beneficial for both the economy and ecology [2]. In 2019, only 17.4% of e-waste was legally collected and adequately recycled out of a total production of 53.6 million metric tons (Mt) worldwide [3]. Subsequently, as consumer technology is constantly evolving, the amount of e-waste is increasing rapidly, and technical innovation

show abstract

A text mining and topic modeling based bibliometric exploration of information science research

Cited by 4 publications

References 22 publications

Topic Modeling for Scientific Articles: Exploring Optimal Hyperparameter Tuning in BERT

Topic Modeling for Scientific Articles: Exploring Optimal Hyperparameter Tuning in BERT

Perbandingan Naïve Bayes dan CNN yang Dioptimasi PSO pada Identifikasi Berita Hoax Politik Indonesia

Current Trend, Future Direction, and Enablers of e-Waste Management: Bibliometric Analysis and Literature Review

Contact Info

Product

Resources

About