000			03124nam a22003257a 4500
003			OSt
005			20250709105147.0
008			250709b |||||||| |||| 00| 0 eng d
040			_aTUPM _bEnglish _cTUPM _dTUPM _erda
050			_aBTH QA 76.9 _bB53 2025
100			_aBiag, Christian Kelly A. _eauthor
245			_aDevelopment of alguard website fake news detector using nlp, lime and cnn-rnn algorithms/ _cChristian Kelly A. Biag, Mark Jason R. Tabiliran, Lance Nathan B. Tubeo, Merham John H. Ungad, and Benjie D. Vega.--
260			_aManila: _bTechnological University of the Philippines, _c2025.
300			_axii, 127pages: _c29cm.
336			_2rdacontent
337			_2rdamedia
338			_2rdacarrier
500			_aBachelor's thesis
502			_aCollege of Industrial Technology.-- _bBachelor of engineering technology major in computer engineering technology: _cTechnological University of the Philippines, _d2025.
504			_aIncludes bibliographic references and index.
520			_aThe study ALGUARD: A Website Fake News Detector using NLP, LIME, CNN-RNN, is made to determine the facts of local online outlets' fake news sources in the Philippines. The goal of this study is to classify and disseminate counterfeit news that is shared on the nation's internet media platforms. and give relevant and accurate analysis on the news. The URL is copied to the scanner sensor QR codes that analyzes the percentage of accuracy of the given news based on the keywords compared with the original and fake news. The sixty percent result must be achieved in the comparison of URLs to the local news sources to identify whether the URL article is authentic or not. The algorithms used are Natural Language Processing (NLP), Local Interpretable Model-agnostic Explanations (LIME), and a Convolutional Neural Network-Recurrent Neural Network (CNN-RNN). The study makes use of an agile development methodology and incorporates iterative testing and enhancements. The system performance was tested F1 scoring, and user feedback from social media users and journalists. There were 30 respondents who were composed of different internet users . The ISO/IEC 25002:2024 instrument of evaluation was used to assess the performance of the ALGUARD system and obtained an overall mean 4.37 which is described as “Very Satisfactory”. This defines the developed system’s capability to detect fake news. This study supports UN-SDG 16 by promoting access to reliable information and protecting media integrity and freedom. UN-SDG 12 helps promote the responsible consumption of fake news on online platforms, reducing fake news articles from spreading online. UN-SDG 11 helps create a safe and reliable internet community through safe and authentic news coverage in the Philippines.
650			_aAlguard
650			_aNatural language processing (nlp)
650			_aLocal interpretable
700			_aTabiliran, Mark Jason R. _eauthor
700			_aTubeo, Lance Nathan B. _eauthor
700			_aUngad, Merham John H. _eauthor
700			_aVega, Benjie D. _eauthor
942			_2lcc _cBTH CIT _n0
999			_c30236 _d30236