Measure brand sentiment.
To track and measure user sentiment, we needed to build a model that would enable us to aggregate the opinions of our client’s Twitter audience over a period of time.
OUR CASE STUDIES
Sentiment analysis
Measure sentiment with machine learning
A multinational company wanted to track user sentiment about its brand on Twitter so it could extract and measure customer perceptions to help inform its advertising and marketing campaigns.
AI
Online chatter can be poorly written and unclear, so our first task was to create a framework to disambiguate the tweets. To meet this challenge, we built a real-time tracker for tweets that used specific hashtags and handles, including tags that referenced our client’s competitors.
After we created a framework to identify, clarify, and target relevant tweets, we then analyzed those tweets to decide if the tweets were positive (favorable) or negative (unfavorable). Once we quantified that data, we were able to chart customer sentiment about our client’s brand versus customer sentiment about competitive brands over a period of time.
our role
- research & development
- develop frontend dashboard to track trends
platforms
- Ruby on Rails
deliverables
- Pre-trained LSTM-based solution
- Final chart with sentiment analysis over time
Jobs to be done
- Understand and measure subjective data
- Develop neural network model
- Extract and measure customer sentiments as favorable or unfavorable
Data and model delivered in one week
This project’s shining point was speed of prototyping. With extensive knowledge of APIs, developer tools, and potential models, we were able to deliver data and a dashboard to our client within one week.