Research that benefits others deserves respect

#Data Collection #Text Analysis #Machine Learning #Multimodal Analysis #Visualization #Statistics & Other


📁 Data Collection

  • Data Collection from Chinese Travel Platforms
    Link

  • Data Collection of Newspaper Information from the U.S. Library of Congress
    Link

  • Data Collection of U.S. Congressional Members Information
    Link

  • Data Collection on African American Enlistment during the U.S. Civil War
    Link

  • Large-Scale County-Level Newspaper Data Collection in the United States
    Link

  • New York Times Data Collection
    Link


📖 Text Analysis

  • A Memory-Efficient, Multithreaded Method for Training Word Embeddings on Ultra-Large-Scale Texts
    Link

  • Analyse Textual Narrative Structure
    Link

  • Analysis of Morality Reflected in Text
    Link

  • Bag-of-Words Model (BoW)
    Link

  • Construct Extended Seed Word Lists from Ultra-Large-Scale Texts Using PMI
    Link

  • Dictionary-based Method
    Link

  • Latent Dirichlet Allocation (LDA)
    Link

  • Text Sentiment Analysis
    Link

  • Use an LLM and SymSpell to Detect Misspelled Words in Text
    Link

  • Use an LLM to Extract Adjectives Describing Specific Entities
    Link

  • Use WordSegment to Correct Recognition Errors in Text
    Link

  • Word Embedding
    Link


🤖 Machine Learning

  • Perform Classification and Prediction Tasks on Web Text Using Different BERT Models
    Link

  • Use the ChatGPT API for Recognition Tasks
    Link

  • Load Models on the Backend and Expose API Endpoints Using FastAPI
    Link


🖼 Multimodal Analysis

  • Calculate Brightness, Hue, and Saturation in Images
    Link

  • Calculate the Color Proportions in Images
    Link

  • Calculation of Average Color Metrics and Facial Features in Images
    Link

  • Facial Emotion Analysis in Short Videos
    Link

  • librosa — Music Analysis
    Link


📊 Visualization

  • Moral Score Visualization
    Link

  • Sentiment Score Visualization
    Link

  • Basic Descriptive Statistics
    Link

  • Plot High-Resolution Maps Using ggplot2 (R)
    Link


📈 Statistics & Other

  • Two-Way Fixed Effects (Stata)
    Link

  • Continuous Difference-in-Differences (DID, R)
    Link

  • Fixed Effects Method (R)
    Link

  • Mediation Analysis Method (R)
    Link

  • Ordinary Regression Methods (R)
    Link

  • Automatically Create MTurk Qualifications to Block Previously Responded Participants (Python)
    Link

  • Automatically Distribute Project Tasks on MTurk (Python)
    Link

  • Automatically Distribute Tasks to Respondents via MTurk (Python)
    Link

Continue…