Lambert  T. Dela Cruz, Marjorie Jasmine C. Racelis.  4  0   <br/><br/>
An Enhancement of support vector machine in context of sentiment analysis applied in scraped data from tripadvisor hotel reviews.        6 
       6     

 -   
 -     
 -         
 -   
 -   
 - 
 - 
 -         .
 -     .
 -          0   .
 -         .
 -  0       .
<br/><br/>   Undergraduate Thesis : (Bachelor of Science in Computer Science) - Pamantasan ng Lungsod ng Maynila, 2024. 
<br/><br/>
<br/><br/>      
<br/><br/>   5 
<br/><br/>      
<br/><br/> ABSTRACT:  With many tourists or travellers visiting different places, accommodation is an essential decision to consider before traveling to a specific destination; however, finding such information is now easy, specifically since there are platforms like TripAdvisor that can help you find a place to stay for your trip. This website has a lot of information or reviews about various hotels. However, the sheer volume of online reviews presents a significant challenge for travellers in discerning the quality of attractions. Due to this, Travelers need to perform a Sentiment Analysis. Sentiment analysis is a technique to extract, identify, and understand sentiments or opinions contained in a text. This study addresses the challenges of long training time, hyperparameter optimization, and imbalanced data in Support Vector Machines (SVM). The study introduces enhancements such as Sequential Minimal Optimization (SMO), Random Search for hyperparameter optimization, and Synthetic Minority Over-sampling Technique (SMOTE) to address these issues. A comparative analysis reveals that the Enhanced SVM (SMO-RandomSearch-SMOTE) significantly outperforms the Traditional SVM, with a 13.48% increase in accuracy and a 100.42% reduction in training time. Precision and F1-Score also saw improvements of 11.5% and 8.5%, respectively. The enhanced SVM model demonstrates its potential in efficiently analyzing sentiments from hotel reviews, aiding tourists in decision-making and improving their travel experience. The findings contribute to the advancement of machine learning and natural language processin g fields, offering insights for future researchers to develop more accurate models for sentiment analysis. In conclusion, the study successfully enhances the SVM algorithm, providing a more effective tool for sentiment analysis in the context of hotel reviews, with significant improvements in performance metrics.       
<br/><br/>      
<br/><br/><br/> <br/> <br/> <br/> <br/> <br/> <br/> 
<br/><br/><br/>5     
<br/><br/><br/> <br/>   
<br/><br/><label>ISBN: </label>  
<br/><br/><label>ISSN: </label>2 
 =   
 =   
<br/><br/><label>Standard No.: </label>        
<br/><br/><label>Publisher. No.: </label>  
<br/><br/><label>Source: </label>        
<br/><br/><label>LCCN: </label>
<br/><br/><label>Nat. Bib. No.: </label> 2 
<br/><br/><label>Nat. Bib. Agency Control No.: </label>    
<br/><br/><label>Subjects--Personal Names: </label><br/>     2     --0------
<br/><br/><label>Subjects--Corporate Names: </label><br/>     6 --0-- 2 --------
<br/><br/><label>Subjects--Meeting Names: </label><br/><br/> 0    2 --
<br/><br/><label>Subjects--Uniform Titles: </label><br/>  --20------
<br/><br/><label>Subjects--Chronological Terms: </label><br/> 
<br/><br/><label>Subjects--Topical Terms: </label><br/>    --------20--
<br/><br/><label>Subjects--Geographic Terms: </label><br/>--------20--
<br/><br/><label>Index Terms--Genre/Form: </label><br/>----2
<br/><br/><label>LC Class. No.: </label> / 2 
<br/><br/><label>Dewey Class. No.: </label> / 2 
<br/><br/><label>National Agricultural Library Call No.: </label> /  
<br/><br/><label>National Library of Medicine Call No.: </label> /  
<br/><br/><label>Gov. Doc. Class. No.: </label>