Performance Comparison of Topic Modeling Algorithms on Indonesian Short Texts

Hidayati, Nuraisa Novia; Parlina, Anne

doi:10.1145/3575882.3575905

Cited by 2 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This strategic filtering addresses LDA's shortcomings in handling brief texts and aligns with its general efficiency when dealing with more extensive textual inputs. This finding aligns with previous research that has highlighted LDA's challenges in modeling concise texts when compared to other advanced topic modeling methods [15]. Departing from prior research that explored a broader range of topic counts, ranging from 40 to 60, with various kernel modifications for SVM [7][8], our study adopts a more focused approach to topic allocation.…”

Section: Discussion and Comparative Analysissupporting

confidence: 81%

“…LDA represents each document as a mixture of latent topics and as a distribution of words from the vocabulary. The steps and parameters that we use in feature extraction using LDA, following our prior study [15], involve a defining the vocabulary of words V, the number of topics K, and document D, where V = {v1, v2, v3, ..., vn}, K = {2, ..., 50}, D = {d1, d2, d3, ..., dm}. We systematically explore the number of topics K to find the most optimum coherence value.…”

Section: Preprocessing Datamentioning

confidence: 99%

See 1 more Smart Citation

Improving Aspect-Based Sentiment Analysis for Hotel Reviews with Latent Dirichlet Allocation and Machine Learning Algorithms

Hidayati

2023

regist. j. ilm. teknol. sist. inf.

View full text Add to dashboard Cite

The rapid expansion of online platforms has resulted in a deluge of user-generated content, emphasizing the need for sentiment analysis to gauge public opinion. Aspect-based sentiment analysis is now essential for uncovering intricate opinions within product reviews, social media posts, and online texts. Despite their potential, the complexity of human emotions and diverse language nuances pose significant challenges. Our study focuses on the importance and trends of sentiment and aspect-based sentiment analysis in automated review analysis, with a primary focus on Indonesian-language hotel reviews. Our research underscores the need for nuanced tools to unravel multifaceted sentiments. We propose an automation framework that utilizes Latent Dirichlet Allocation (LDA) for feature extraction. We evaluate LDA's performance, enhance it through filtration, and enrich it by integrating it with Word2Vec and Doc2Vec. Our methodology encompasses various machine learning algorithms, including Logistic Regression (LR), Stochastic Gradient Descent (SGD), Support Vector Machine (SVM), Random Forest (RF), and Light Gradient Boosting Machine (LGBM). Empirical results reveal that the optimal combination involves LDA bigram and Word2Vec, alongside the LGBM classifier, yielding an average F1 score of 86.6 across ten aspects. This contribution advances automated aspect-based sentiment analysis, offering concrete implications for e-commerce, marketing, and customer service. Our insights inform precise marketing strategies and enhance customer experiences, underscoring the research's relevance in the digital landscape.

show abstract

Section: Discussion and Comparative Analysissupporting

confidence: 81%

Section: Preprocessing Datamentioning

confidence: 99%

Improving Aspect-Based Sentiment Analysis for Hotel Reviews with Latent Dirichlet Allocation and Machine Learning Algorithms

Hidayati

2023

regist. j. ilm. teknol. sist. inf.

View full text Add to dashboard Cite

show abstract

“…This likelihood serves for model comparison, where a higher likelihood indicates a superior model. The perplexity of held-out texts often serves as a measure for topic models and is defined in (7).…”

Section: Perplexitymentioning

confidence: 99%

“…However, concerning the Indonesian language, additional investigation is essential to refine techniques for generating more accurate and important topic models [6]. Hidayati and Parlina [7] on comparison of topic modeling algorithm performance on Indonesian short texts which compares the topic extraction performance of LDA, non-negative matrix factorization (NMF), and gibbs sampling dirichlet multinomial mixture (GSDMM) algorithms from short Indonesian texts. This study found that LDA outperformed NMF and GSDMM regarding topic coherence scores, but human judgment showed that the word clusters generated by NMF and GSDMM were easier to infer.…”

Section: Introductionmentioning

confidence: 99%

Improving the term weighting log entropy of latent dirichlet allocation

Muhajir,

Rosadi,

Danardono

2024

IJEECS

View full text Add to dashboard Cite

<p class="AbstractText">The process of analyzing textual data involves the utilization of topic modeling techniques to uncover latent subjects within documents. The presence of numerous short texts in the Indonesian language poses additional challenges in the field of topic modeling. This study presents a substantial enhancement to the term weighting log entropy (TWLE) approach within the latent dirichlet allocation (LDA) framework, specifically tailored for topic modeling of Indonesian short texts. This work places significant emphasis on the utilization of LDA for word weighting. The research endeavor aimed to enhance the coherence and interpretability of an Indonesian topic model through the integration of local and global weights. Local Weight focuses on the distinct characteristics of each document, whereas global weight examines the broader perspective of the entire corpus of documents. The objective was to enhance the effectiveness of LDA themes by this amalgamation. The TWLE model of LDA was found to be more informative and effective than the TF-IDF LDA when compared with short Indonesian text. This work improves topic modeling in brief Indonesian compositions. Transfer learning for NLP and Indonesian language adaptation helps improve subject analysis knowledge and precision, this could boost NLP and topic modeling in Indonesian.</p>

show abstract

Performance Comparison of Topic Modeling Algorithms on Indonesian Short Texts

Cited by 2 publications

References 11 publications

Improving Aspect-Based Sentiment Analysis for Hotel Reviews with Latent Dirichlet Allocation and Machine Learning Algorithms

Improving Aspect-Based Sentiment Analysis for Hotel Reviews with Latent Dirichlet Allocation and Machine Learning Algorithms

Improving the term weighting log entropy of latent dirichlet allocation

Contact Info

Product

Resources

About