Inspiration
The goal was to leverage the Hex.tech analytics stack to analyze Gen Z Slang. The dataset was from HuggingFace.
What it does
It analyzes the rich collection of popular slang terms and definition used by Generation Z. It uses the Hex thread agent as a starting point for the analysis. This was also the major challenge, trying to narrow down the analysis to be used. After reviewing the output of the Hex thread agent, I then built out more of the analysis in the notebook using python primarily. I then added visualizations using plotly. From there I built out the application.
How we built it
The app was built using the Hex platform. I used a mix of python, different python libraries for text analysis and visualization.
Challenges we ran into
- One challenge was exploring the different aspects of the Hex platform. It is quite expansive and has lots of ways to do analytics. You can dive right into doing your analysis with your own dataset or import from snowflake or another external datasource. So had to know which approach would be best for my project. I went with importing my own dataset from HuggingFace.
- Another major challenge was knowing what questions to ask when leveraging the thread or notebook agent. Since you could go with a simple prompt or something deeper. I started with popular text analysis approaches as the starting point. I then reviewed the data first. I also made changes to the analysis to make them more robust. It was definitely a challenge. Lastly, I added some terms to the different section to make them more user friendly for those not familiar with text analysis.
## Key Insights - Based on topic modeling the key slangs are social media and gaming focused
- Using sentiment analysis showed that Gen Z uses a lot of neutral terms in their slang
- Using trend analysis showed a lot of slangs are cultural staples and there aren't that many viral slangs
- Using community analysis showed there are very distinct sub-clutures in how GenZ uses slangs ## Accomplishments that we're proud of
- Ability to go from analysis to user friendly app in a short period of time using the Hex platform ## What we learned
- Loved the approach to analytics leveraging LLMs but still giving the end user the ability to write python, SQL and hopefully R
- Great experience learning how to use the hex platform in terms of the widgets, presentation, sharing and visualizations tools ## What's next for SlangZ
- Explore other NLP techniques
Log in or sign up for Devpost to join the conversation.