Evaluasi Topik Tersembunyi Berdasarkan Aspect Extractionmenggunakan PengembanganLatent Dirichlet Allocation

Evaluasi Topik Tersembunyi Berdasarkan Aspect Extractionmenggunakan PengembanganLatent Dirichlet Allocation

sentiment analysis, aspect, topic, extraction, LDA, evaluation

Recently, Sentiment Analysis is used forexpression detection of products or services. Sentiment Analysis is one categorytypewith a level of aspect focusedon extracting productaspects. One of the common methods used for aspect extraction is Latent Dirichlet Allocation (LDA) usingrandom topic identification, but this method has not been able to find an acceptable topic with some aspects havingbeen found. Undeterminable topics arereferred to as the hidden topics. This studypurposeis to evaluateand comparethe suitability of identifying hidden topics between human and computer evaluation. The study is also focused on aspect extraction using a variety of LDA innovations.The data used in this study used case studies on e-Commerce. Data were processed using feature selection and grouped using LDA development.Then the dataresultsare processed using Latent Topic Identification basedonsubjective and objective evaluations. The identification of hidden topicresultswasevaluated using several semantic and lexicon tests.The evaluation results indicate the comparisonoftwo hidden topic identification assessmentvaluesis quite relevant with the average difference in value reaching 6%. As a result, computer calculations assist humans in determining topics if each topic has a low coherence value

Dinda Adimanggala1, Fitra A. Bachtiar2, Eko Setiawan3

https://jurnal.iaii.or.id/index.php/RESTI/issue/view/23

Universitas Brawijaya

20 juni 2021

Fajar bagus W

PDF

Indonesia

Text