This repository houses a Python tool designed to analyze customer reviews from Apple Store and Google play store and develop user empathy and insights.
- Link to blog: Develop User Empathy and Craft Better Products: Using Machine Learning to Analyze User Feedback via Clustering & Sentiment Analysis
- Techniques to download reviews from Apple app store and Google Play store for further analysis.
- Develop actionable innovation strategies by harnessing the power of advanced machine learning techniques such as SentimentIntensityAnalyzer using Valence Aware Dictionary and sEntiment Reasoner(VADER), Clustering using KMeans and Term Frequency-Inverse Document Frequency (TF-IDF), and EDA techniques including wordcloud creation.
Background and Objective:
Qualitative research provides in-depth user insights which helps in understanding of reasons, opinions, motivations, and underlying meanings. It helps in unearthing insights which are often missed in qualitative research. However due to nature of data common statistical approach can’t be easily applied to qualitative data and therefore it is time consuming to analyze, and be dependent on interpretation and biases of researchers.
Sentiment Analysis and Clustering techniques makes it a lot easier in analyzing qualitative data and developing insights. By using statistical machine learning techniques we can reduce interpretation biases, and make the analysis more data informed.
Following code downloads 2000 user reviews for Headspace App on Apple App Store and Google Play store. The code uses machine learning to do sentiment analysis on user reviews and creates clusters. The code then does some exploratory data analysis for each of the cluster.
This helps us in identifying common themes across cluster and develop insights which can be used to improve user experience and consequently improve life time value of the users.
- Install required libraries: use pip install section to install required python packages to run the program.
- How to run: Open User_Review_Analysis_HeadSpace_App.ipynb in colab notebook to run the application.
This tool is intended for education and informational purposes only.