User Perception Analysis of Online Learning Platform “Zenius” During the Coronavirus Pandemic Using Text Mining Techniques

Akbar, Arminditya Fajri; Santoso, Harry Budi; Putra, Panca O. Hadi; Yudhoatmojo, Satrio Bhaskoro

doi:10.21609/jsi.v17i2.1065

Cited by 5 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Case folding is then performed to ensure that the text is standardized in terms of the case. This process ensures that machine learning models interpret words with different character cases (e.g., ''You'' and ''YOU'') in the same way, minimizing the likelihood that the model will weigh identical words differently [45], [46].…”

Section: ) Case Foldingmentioning

confidence: 99%

“…Token cleansing is also performed, which includes several sub-processes, such as accent and diacritic normalization, where words like ''cliché'' are changed to ''cliche'' to reduce the variety of tokens. Additionally, the removal of links, punctuation, numbers, and non-Latin characters is also carried out to keep the focus on meaningful content [45], [46].…”

Section: ) Token Cleansingmentioning

confidence: 99%

“…Stopword removal is performed to discard words that frequently appear in the text but do not contribute to its meaning [45], [46]. The list of stopwords used is a combination of Indonesian and English stopwords provided by the Natural Language Toolkit (NLTK) library [47].…”

Section: ) Stopword Removalmentioning

confidence: 99%

“…Lemmatization, as the final preprocessing step, is performed to reduce words to their base forms. This aims to ensure that derived words are interpreted in the same way by the model [45], [46], allowing the model to treat the variations of a word as a single token. For lemmatization, the stanfordnlp library with its Indonesian NLP pipeline is used to find the lemma of Indonesian text [48], and spacy is used for English text [49].…”

Section: ) Lemmatizationmentioning

confidence: 99%

See 3 more Smart Citations

LDAViewer: An Automatic Language-Agnostic System for Discovering State-of-the-Art Topics in Research Using Topic Modeling, Bidirectional Encoder Representations From Transformers, and Entity Linking

Dillan

Fudholi

2023

IEEE Access

View full text Add to dashboard Cite

Advancements in knowledge are pivotal to academic progress, necessitating efficient methods for discovering the state-of-the-art in various fields. Existing approaches, however, are language-specific and lack automation, limiting their efficacy. This study aims to develop a language-agnostic software that streamlines the process of identifying state-of-the-art research across diverse academic topics. The software automatically retrieves articles from multiple databases and preprocesses the content through tokenization, case folding, token cleansing, stopword removal, and lemmatization. Subsequently, a numeric documentphrase matrix is created and analyzed using latent Dirichlet allocation (LDA) and bidirectional encoder representations from transformers (BERT) to discover and label topics automatically. The study introduces a novel topic-filtering method based on entity linking and filtering model outputs using a knowledge database to ensure topic relevance. The visual representation employs nested bubble and line charts, effectively illustrating current topics, gaps, and research evolution trends. A user survey spread to 52 student researchers assessing the interface, topic relevance, and research output of the developed software, revealed that the interface is user-friendly, easy to navigate, and the presented information is comprehensible. Survey results also indicated that the generated topics are consistent with the processed article content and relevant to the investigated topic. The visualization effectively aids in understanding the state-of-the-art and research map. This study demonstrates that integrating LDA, BERT, and the proposed topic filtering and labeling method yields a robust tool for preliminary research analysis with high precision and relevance.INDEX TERMS Topic modeling, state-of-the-art discovery, development of knowledge, latent-dirichlet allocation, bidirectional encoder representations from transformers, entity linking.

show abstract

Section: ) Case Foldingmentioning

confidence: 99%

Section: ) Token Cleansingmentioning

confidence: 99%

Section: ) Stopword Removalmentioning

confidence: 99%

Section: ) Lemmatizationmentioning

confidence: 99%

See 2 more Smart Citations

LDAViewer: An Automatic Language-Agnostic System for Discovering State-of-the-Art Topics in Research Using Topic Modeling, Bidirectional Encoder Representations From Transformers, and Entity Linking

Dillan

Fudholi

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Entities include individuals, organizations, events, and subjects, among other things [20]. The primary focus of both sentiment analysis and topic modeling is on the activity of dataset exploration [21]. The fields of marketing, healthcare, banking, and politics are just some of the areas that are frequently investigated for their potential applications of sentiment analysis of social media [22].…”

Section: Introductionmentioning

confidence: 99%

Sentiment Analysis Against Political Figure’s Billboard During Pandemic Using Naïve Bayes Algorithm

Bastian

Mardiana

Wulansari

2023

J. RESTI (Rekayasa Sist. Teknol. Inf.)

View full text Add to dashboard Cite

In the midst of the Covid-19 Pandemic, many Indonesians have reacted negatively to the placement of political individuals' billboards with very huge sizes on the streets. The early political campaign that was run was thought to be contentious. On social media like Twitter, the majority of people freely share their thoughts. The purpose of this study is to investigate how the general public reacted to the placement of billboards advertising political figures during the epidemic and to categorize those responses. It is envisaged that it would also provide advice for connected parties that may be used when making judgments regarding the policy of constructing billboards for political figures during a pandemic based on the results of data analysis. Twitter users tend to be more expressive because of the character limits, which means they have sentimental or emotional values. Using the Nave Bayes Algorithm, it is possible to do sentiment analysis on the sentiment data by categorizing user comments into positive, negative, and neutral attitudes. Regarding the sentiments expressed on billboards showing political leaders during the pandemic, tweets were sorted into three categories: liked, unfavorable, and neutral. The accuracy rate from Naive Bayes categorization of political personalities during the pandemic on social media Twitter was 83.3% with a precision value of 89%, recall 83%, and f-1 score of 82%.

show abstract

Sentiment analysis on examining students’ opinions regarding NDUM e-learning during COVID-19

Marzukhi,

Aman,

Awang

et al. 2024

AIP Conference Proceedings

View full text Add to dashboard Cite

User Perception Analysis of Online Learning Platform “Zenius” During the Coronavirus Pandemic Using Text Mining Techniques

Cited by 5 publications

References 14 publications

LDAViewer: An Automatic Language-Agnostic System for Discovering State-of-the-Art Topics in Research Using Topic Modeling, Bidirectional Encoder Representations From Transformers, and Entity Linking

LDAViewer: An Automatic Language-Agnostic System for Discovering State-of-the-Art Topics in Research Using Topic Modeling, Bidirectional Encoder Representations From Transformers, and Entity Linking

Sentiment Analysis Against Political Figure’s Billboard During Pandemic Using Naïve Bayes Algorithm

Sentiment analysis on examining students’ opinions regarding NDUM e-learning during COVID-19

Contact Info

Product

Resources

About