This project is focused on analyzing consumer sentiments for melatonin products listed on Amazon. By leveraging natural language processing (NLP) techniques and visualization tools, we aim to uncover insights into user preferences, product attributes, and overall sentiment trends to aid better product understanding and marketing strategies.
The goal of this project is to:
- Understand Consumer Sentiments: Analyze the textual reviews to gauge customer opinions.
- Identify Patterns: Extract meaningful insights regarding product attributes such as flavor, dosage, and form (e.g., gummy or tablet).
- Explore Usage Preferences: Examine how timing, duration, and usage phrases affect user experiences and sentiments.
- Visualize Key Findings: Provide interactive and static visualizations to convey the insights effectively.
- Performed polarity-based sentiment scoring to classify reviews into positive, neutral, or negative categories.
- Identified trends in consumer satisfaction based on key product attributes such as flavor and dosage.
- Cleaned and preprocessed the textual reviews using techniques like tokenization, stemming, lemmatization, and stop-word removal.
- Extracted key phrases such as "usage timing" and "duration of use" to gain deeper insights into consumer behavior.
- Average Sentiment by Flavor:
- A horizontal bar chart to highlight which flavors receive the highest and lowest sentiments.
- Interactive Plotly visualization with a color scale to differentiate sentiment intensity.
- Average Sentiment by Usage Phrases:
- A bar chart showcasing how user-described usage scenarios (e.g., "30 minutes before bed") correlate with sentiment scores.
- Insights on user preferences for flavors, dosage forms, and timing for taking melatonin.
- Patterns in long-term vs. short-term product usage and their corresponding sentiments.
- Recommendations for product improvement and marketing strategies.
- Languages: Python
- Libraries:
- Data Analysis: Pandas, NumPy
- Natural Language Processing: NLTK, TextBlob
- Visualization: Matplotlib, Seaborn, Plotly
- Tools: Jupyter Notebook
- Average Sentiment by Flavor:
- Helps identify which flavors are most appreciated by users.
- Provides actionable insights for product development.
- Average Sentiment by Usage Phrases:
- Offers a deep dive into how consumers use melatonin and their satisfaction levels.
- Clone the repository:
git clone https://github.com/yourusername/melatonin-sentiment-analysis.git
- Install the required Python libraries:
pip install -r requirements.txt
- Open the Jupyter Notebook:
jupyter notebook
- Run the
TEAM2-DATASCIENCEPROJECT(AMAZON ADULTS).ipynbfile.
Contributions are welcome! Feel free to fork the repository and submit a pull request.
- Data collected from Amazon reviews.
- Thanks to team members and collaborators who contributed to this project.
Let me know if you need further customization for your README!