Prediction of research trends using LDA based topic modeling

Gupta, Rahul Kumar; Agarwalla, Ritu; Naik, Bukya Hemanth; Evuri, Joythish Reddy; Thapa, Apil; Singh, Thoudam Doren

doi:10.1016/j.gltp.2022.03.015

Cited by 35 publications

(33 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Therefore, they were removed in the preprocessing stage Lemmatization . This step reduces conjunction words and contributes to retrieving or fetching valid and essential words [ 12 ]. At this stage, the words were converted to their roots Conversion of texts to numeric vectors The next step is vectorization because most machine learning techniques only work with numerical data, so in order to use and apply these techniques to textual data, it is necessary to convert the texts into a set of numbers.…”

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

“…Moreover, Gupta et al, in a study entitled “Prediction of the research process using the LDA-based topic modeling,” focused on discovering paradigms as predictors with the relevance of each topic through topic modeling techniques such as LDA with the BoW [ 12 ]. Many previous studies have evaluated bioinformatics with scientometric algorithms and word analysis, and some researchers have discovered latent patterns using text mining algorithms [ 10 – 12 ]. Moreover, some other researchers focused on the topic modeling of scientific productions in databases.…”

Section: Introduction and Problem Statementmentioning

confidence: 99%

“…This research was performed using a descriptiveanalytical method through coword analysis techniques. Moreover, Gupta et al, in a study entitled "Prediction of the research process using the LDA-based topic modeling," focused on discovering paradigms as predictors with the relevance of each topic through topic modeling techniques such as LDA with the BoW [12]. Many previous studies have evaluated bioinformatics with scientometric algorithms and word analysis, and some researchers have discovered latent patterns using text mining algorithms [10][11][12].…”

Section: Introduction and Problem Statementmentioning

confidence: 99%

See 3 more Smart Citations

Analysis of Persian Bioinformatics Research with Topic Modeling

Ebrahimi

Dehghani

Makkizadeh

2023

BioMed Research International

View full text Add to dashboard Cite

Purpose. As a scientific field, bioinformatics has drawn remarkable attention from various fields, such as information technology, mathematics, and modern biological sciences, in recent years. The topic models originating from the field of natural language processing have become the focus of attention with the rapid accumulation of biological datasets. Thus, this research is aimed at modeling the topic content of the bioinformatics literature presented by Iranian researchers in the Scopus Citation Database. Methodology. This research was a descriptive-exploratory study, and the studied population included 3899 papers indexed in the Scopus database, which had been indexed in this database until March 9, 2022. The topic modeling was then performed on the abstracts and titles of the papers. A combination of LDA and TF-IDF was utilized for topic modeling. Findings. The data analysis with topic modeling resulted in identifying seven main topics “Molecular Modeling,” “Gene Expression,” “Biomarker,” “Coronavirus,” “Immunoinformatics,” “Cancer Bioinformatics,” and “Systems Biology.” Moreover, “Systems Biology” and “Coronavirus” had the largest and smallest clusters, respectively. Conclusion. The present investigation demonstrated an acceptable performance for the LDA algorithm in classifying the topics included in this field. The extracted topic clusters indicated excellent consistency and topic connection with each other.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introduction and Problem Statementmentioning

confidence: 99%

Section: Introduction and Problem Statementmentioning

confidence: 99%

See 2 more Smart Citations

Analysis of Persian Bioinformatics Research with Topic Modeling

Ebrahimi

Dehghani

Makkizadeh

2023

BioMed Research International

View full text Add to dashboard Cite

show abstract

“…Jika nilai beta tinggi, maka ketergantungan sebuah topik terhadap kata -kata terntu akan lebih menyebar. Sementara jika nilai beta rendah, maka ketergantungan sebuah topik akan lebih terkonsentrasi kepada beberapa atau bahkan satu kata saja [12].…”

Section: Hyperparameter Tuningunclassified

Analisis Ulasan Aplikasi MyPertamina Menggunakan Topic Modeling dengan Latent Dirichlet Allocation

Abdurrazzaq¹

2023

Kalbiscientia

View full text Add to dashboard Cite

Kebijakan untuk menggunakan aplikasi MyPertamina dalam pembelian Bahan Bakar Minyak (BBM) bersubsidi dimulai pada tanggal 1 Juli 2022. Hingga tanggal 17 Agustus 2022, kebutuhan yang besar terhadap BBM di masyarakat membuat kebijakan ini menjadi perhatian. Pengembang aplikasi dapat memperbaiki serta memperbarui aplikasi sesuai dengan keluhan dan ulasan pengguna. Penelitian ini bertujuan untuk memetakan permasalahan yang ada pada aplikasi MyPertamina yang banyak dikeluhkan penggunanya menggunakan topic modeling dengan algoritma LDA. Hasil penelitian membagi komentar menjadi 7 dengan nilai perplexity -8.08844 dan topic coherence 0.49860. Topik – topik tersebut terkait tentang kecemasan pengguna terhadap kebijakan penggunaan aplikasi MyPertamina, permasalahan pada proses pendaftaran, permasalahan pada proses autentikasi, dan permasalahan pada kelancaran penggunaan aplikasi terkait bug dan sinyal. Terdapat 5341 komentar dianggap sebagai spam yang tidak berkorelasi dengan aplikasi MyPertamina.

show abstract