Skip to content

cyn900/JSC370-project

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

74 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Understanding User Behavior and Platform Usage in Jargon

Overview

Jargon is an innovative Chrome extension launched in June 2024, designed to transform English web content into interactive language learning opportunities. The extension offers users the ability to learn various languages, including Spanish and Chinese, and adapt English styles like GRE vocabulary and TikTok slang. For more information, visit official website or the Chrome Web Store.

Key Features

  • Language Learning: Users can select from multiple languages for learning or language style adaptations.
  • Customization Options: Includes difficulty settings, daily target questions, and percentage of text to be highlighted for practice.
  • User Interface: Offers both highlight and underline styles for text selection.
  • Dynamic Learning: Engages users with AI-powered transformations that maintain the original meaning while adapting to different language registers.

Research Objectives

The study focuses on:

  1. Usage Context and Platform Patterns: To identify how users integrate Jargon into their daily web interactions.
  2. Feature Adoption and User Success: To determine which features enhance user engagement and success.

Methods

Data Collection

Data was sourced from Jargon’s Supabase database, covering interactions from the launch up to March 16, 2025. The dataset includes user profiles, interaction records, and settings across five main tables.

Analysis Techniques

  • Sentiment Analysis: Analyzed user feedback to assess overall sentiment towards platform features.
  • LDA Analysis: Utilized Latent Dirichlet Allocation to identify key topics within user feedback and documentation.
  • Correlation Analysis: Investigated relationships between various user engagement metrics and feature preferences.
  • Cluster Analysis: Employed K-means clustering to categorize users into very active, active, and less active groups based on their engagement patterns.
  • Regression Analysis: Used ordinal regression models to evaluate the influence of specific features on levels of user engagement.

Summary and Next Steps

Diverse User Engagement

  • Contextual Versatility: Spanish is the most popular language among users who engage with Jargon across a diverse range of sites.

Impact of Features on User Engagement

  • Optimizing Features: Features such as goal setting and interface preferences (highlight vs. underline styles) significantly influence engagement. Optimizing these based on user feedback and behavioral patterns can drive higher satisfaction and retention.

Personalized User Experiences

  • Customized Strategies: Developing personalized engagement strategies for different user segments could markedly improve platform effectiveness. This includes tailoring onboarding, feature discovery, and interactions to individual preferences and usage patterns.

Enhanced Data Collection and Utilization

  • Data-Driven Enhancements: Improving data collection methods to more precisely capture user interactions and adapting features to align with local time zones can offer more personalized and contextually relevant experiences.

By leveraging these insights, Jargon aims to not only enhance user engagement but also ensure that the platform continues to evolve in line with user needs and preferences, fostering a productive and satisfying learning environment.

For detailed analysis, please refer to the final report and video presentation.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages