Recommender System for Topic Articles based on Forum Trending using Multilayer Perceptron
Sri Hesti Mahanani1, Tuga Mauritsius2
1Sri Hesti Mahanani, Information System Management Department, BINUS Graduated Program, Master Information System Management Bina Nusantara University, Jakarta, Indonesia.
2Tuga Mauritsius, Information System Management Department, BINUS Graduated Program Master Information System Management Bina Nusantara University, Jakarta, Indonesia.
Manuscript received on March 16, 2020. | Revised Manuscript received on March 24, 2020. | Manuscript published on March 30, 2020. | PP: 2478-2486 | Volume-8 Issue-6, March 2020. | Retrieval Number: F8194038620 /2020©BEIESP | DOI: 10.35940/ijrte.F8194.038620
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: SehatQ is a portal and application that helps manage personal and family health. One of SehatQ’s services is providing information and directories in the form of articles. To improve relations with web visitors, SehatQ also provides services in the form of discussion forums. The forum actually contains a variety of topics and changes very quickly over time, so to identify a topic from a collection of forums is very difficult and time-consuming if done manually by humans. But unfortunately the SehatQ editorial team has limited time and human resources in sorting out information sourced from the SehatQ forum to draw conclusions as a topic in the article. This research will offer a solution in analyzing Topic modeling using text mining with the Multilayer perceptron algorithm to provide trending information on the topics most frequently discussed at the forum at a certain time.
Keywords: Data Mining, Tf-Idf, Multilayer Perceptron, Dv-Ngram, N-Gram, Topik Modeling, Big Data, Bahasa.
Scope of the Article: Data Mining.