02550nam a2200265 i 4500003000500000005001700005008004100022040002500063100004000088245011000128300001600238336002100254337002500275338002300300502009300323504003900416520156800455700003902023700003602062700003102098720003002129720004602159720003802205720004102243CSPC20250814093326.0250814s2023    ph a     b    000 0 eng d  aCSPCbengcCSPCerda1 aCernechez, James Lorenz P.eauthor.10aSentiment analysis on filipino food recipe facebook comments /cJames Lorenz P. Cernechez [and 3 others].  a132 leaves.  2rdacontentatext  2rdamediaaunmediated  2rdacarrieravolume  aUndergraduate Thesis (BSCS) - Computer SciencecCamarines Sur Polytechnic Colleges, 2023  aIncludes bibliographic references.3 aThe study explores the sentiment analysis applied to Filipino food recipes shared on Facebook, addressing the lack of research in understanding sentiments expressed in user comments. Using the Naïve algorithm, the study categorized sentiments into positive, neg-ative, or neutral, offering a valuable tool for stakeholders, particularly food vloggers. It recognizes the challenges posed by the diverse nature of Filipino cuisine and linguistic variations in comments. Emphasizing the significance of sentiment analysis in social me-dia data mining, especially on influential platforms like Facebook, the study focuses on deciphering public opinion and user preferences surrounding Filipino food recipes. The problem statement highlights the need for a specialized tool to understand sentiments in Facebook comments, crucial for food vloggers seeking to enhance their online presence. The study outlines systematic objectives, including building, evaluating, and applying a Naïve Bayes model for sentiment analysis. Employing exploratory research methodology on a dataset of 5,000 Filipino food recipe comments, the study unveils patterns and themes in sentiments. The results highlight the accuracy (77.87%), precision (79.10%), recall (68.76%), and F-1 Score (72.26%) of the Naïve Bayes model, indicating its effectiveness in sentiment classification. The conclusion emphasizes the algorithm's systematic frame-work and potential impact on real-world scenarios, offering a tangible tool for stakeholders to understand and respond to user feedback promptly.1 aIbarreta, Carl Francis C.eauthor.1 aMonte, Erika Sheena L.eauthor.1 aSiano, Jessica G.eauthor.  aOnesa, Rosel O.eadviser.  aFortuno, Kaela Marie N.echair, panelist.  aPandes, Tiffany Lyn O.epanelist.  aVelasco, Kezia Abegail T.epanelist.