A text classification on the downstreaming potential of biomedicine publications in Indonesia

Silalahi, Mesnan; Hardiyati, Ria; Nadhiroh, Irene Muflikh; Handayani, Tri; Amelia, Mia; Rahmaida, Rizka

doi:10.1109/icoiact.2018.8350778

Cited by 3 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Naive Bayes algorithm, a probabilistic connection between features (attributes) and classes (labels) is actually employed. The naive part of this algorithm is that the assumption of independence between features may not carry out every time [35].…”

Section: Machine Learning Methodsmentioning

confidence: 99%

Development of content‐based SMS classification application by using Word2Vec‐based feature extraction

Ballı

Karasoy

2019

IET softw.

View full text Add to dashboard Cite

While mobile instant messaging applications such as WhatsApp, Messenger, Viber offer benefits to phone users such as price, easy usage, stable, collective and direct communication, SMS (short message service) is still considered a more reliable privacy-preserving technology for mobile communication. This situation directs the institutions that want to perform the product promotion such as advertising, informing, promotion etc. to use SMS. However, spam messages sent from unknown sources constitute a serious problem for SMS recipients. In this study, a content-based classification model which uses the machine learning to filter out unwanted messages is proposed. From the selected dataset, the model to be used in the classification is created with the help of Word2Vec word embedding tool. Thanks to this model, two new features are revealed for calculating the distances of messages to spam and ham words. The performances of the classification algorithms are compared by taking these two new features into consideration. The random forest method succeeded with a correct accuracy rate of 99.64%. In comparison to other studies using the same dataset, more successful correct classification percentage is achieved.

show abstract

Section: Machine Learning Methodsmentioning

confidence: 99%

Development of content‐based SMS classification application by using Word2Vec‐based feature extraction

Ballı

Karasoy

2019

IET softw.

View full text Add to dashboard Cite

show abstract

“…For the purposes of this study, the downstreaming concept is proxied by assuming that the further the publication of the research results in the drug design process, the higher the potential for downstreaming of the results of the study. (Silalahi et al, 2018b). The document classification model is divided into four stages, where the first phase of basic research is seen as a small potential still far from downstream, while the clinical trial stage is seen as to have the greatest potential for downstreaming.…”

Section: B Research Downstreaming Processmentioning

confidence: 99%

“…Distribution of Indonesian biomedicine research publication based on drug research and development category(Silalahi et al, 2018b) …”

mentioning

confidence: 99%

A Contextual Scientometric Analysis of Indonesian Biomedicine : Mapping The Potential of Basic Research Downstreaming

Hardiyati¹,

Nadhiroh²,

Handayani³

et al. 2018

STIPM Journal

Self Cite

View full text Add to dashboard Cite

<p>A content analysis on Indonesian biomedical research publication is conducted based on text mining. The research is necessary to obtain a rich contextual overview of the development of biomedicine research in Indonesia for example in the context of the downstreaming potential of research publications. The results of text data processing using a computational model and bibliometric analysis will provide a richer contextual picture as a proxy to reveal the potential for downstreaming of basic research. Quantitative research is conducted using data sources from Scopus, Google Scholar and universities’s and scientific journal’s repository to analyse the performance at the meso and macro level. Interpretation of the results is qualitatively carried out within a FGD session with domain experts. An attempt is carried out to see the trajectory of series of research publications from basic research stage down to clinical trials. This effort results in an ability to show the research trajectory in anti-malaria drug development from the basic research which evolves to the clinical trial. This study reveals many discontinuities in the trajectory a research topic from basic research to downstreaming in drugs development in Indonesia.</p>

show abstract

“…The researchers conducted the study both individually and collaboratively. The collaboration carried out only between ASEAN countries is defined as regional collaboration (Amelia, Nadhiroh, Rahmaida, Hardiyati, & Handayani, 2017). Research collaboration itself can be characterized as a form of collaboration carried out by one or two or more people (researchers) to achieve a common goal of producing a work (Arlianis, 2016) Author collaboration occurs due to several factors, which include first, personal factors, namely motivation, and interest in participating; second, professional factors, which involve experience and skills as well as the quality of research problems; the third factor is the factor of research organizations and collaboration of national and international organizations (Rusdi et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Islamic Media Bibliometric analysis based on scientific publications in ASEAN countries

Febriani

Maika

2023

J. Kaji. Inf. Perpust.

View full text Add to dashboard Cite

Islamic media has a role in economic development, as seen from the many institutions in ASEAN countries that conduct research on various forms of Islamic media and make it a nationally and internationally indexed scientific publication. However, researchers have yet to find any study on ASEAN countries' cooperation in searching for scientific works on the theme of Islamic media, which were analyzed using the R-Package software application. Therefore, this study aimed to determine Islamic Media Bibliometric analysis based on scientific publications in ASEAN countries through study the core information, the number of the most relevant authors, the number of countries' scientific production, types of documents, active affiliations, and the conceptual structure of scientific publications in Islamic media in ASEAN countries. This research used the bibliometric analysis method. Data was collected by searching the Scopus database for Islamic media keywords based on articles, titles, and keywords. The study results obtained 280 documents from 2007 to 2021, including articles and conference papers. Malaysia had the highest number of countries' scientific production in Islamic media scientific publications in ASEAN countries, with 228 frequencies. According to the highest number of scientific publications in Islamic media in ASEAN countries, the National University of Malaysia has produced the highest number of active institutions (31 frequencies). In addition, the study results already include core information containing key data, document types, document contents, authors, and author collaborations needed in this study.

show abstract

A text classification on the downstreaming potential of biomedicine publications in Indonesia

Cited by 3 publications

References 8 publications

Development of content‐based SMS classification application by using Word2Vec‐based feature extraction

Development of content‐based SMS classification application by using Word2Vec‐based feature extraction

A Contextual Scientometric Analysis of Indonesian Biomedicine : Mapping The Potential of Basic Research Downstreaming

Islamic Media Bibliometric analysis based on scientific publications in ASEAN countries

Contact Info

Product

Resources

About