FUTURE_DS_03 – College Event Feedback Analysis

Internship Program

Future Interns – Data Science & Analytics Internship

---

📌 Task Description

This repository contains Task 3 of the Data Science & Analytics Internship program.
The task focuses on analyzing student feedback collected after college events to extract meaningful insights using data analysis and Natural Language Processing (NLP).

The goal is to understand student satisfaction, identify common feedback patterns, and provide actionable recommendations that can help improve future campus events.

---

🎯 Objectives

The key objectives of this task are:

• Clean and prepare feedback data collected via a Google Forms–style dataset
• Analyze student satisfaction ratings on a 1–5 scale
• Apply NLP techniques to classify feedback sentiment (Positive / Neutral / Negative)
• Visualize insights using charts and graphs
• Suggest data-driven improvements for future event planning

---

📂 Dataset Information

• File: student_feedback.csv
• Type: Simulated Google Forms feedback dataset
• Contents:
  • Event name and event type
  • Hosting department
  • Student rating (1–5 scale)
  • Textual feedback comments

The dataset simulates real-world feedback collected after college events such as workshops, seminars, cultural programs, and tech fests.

---

🛠 Tools & Technologies Used

• Python – Core programming language
• Google Colab – Cloud-based notebook environment
• pandas – Data cleaning and manipulation
• TextBlob – NLP-based sentiment analysis
• Matplotlib – Data visualization

---

🔍 Analysis Performed

1️⃣ Data Cleaning & Preparation

• Removed missing or inconsistent values
• Converted rating values into numeric format
• Ensured the dataset was ready for analysis

2️⃣ Rating Analysis

• Calculated average ratings across event types
• Identified top-performing events
• Analyzed satisfaction patterns to understand student preferences

3️⃣ Sentiment Analysis (NLP)

• Classified feedback comments into:
  • Positive
  • Neutral
  • Negative
• Visualized sentiment distribution using a pie chart
• Extracted common feedback themes using a word cloud

4️⃣ Data Visualization

• Bar chart showing average rating by event type
• Pie chart summarizing sentiment distribution
• Word cloud highlighting frequently used feedback terms

---

📊 Key Insights

• Workshops and interactive events received higher satisfaction ratings
• Passive event formats showed comparatively lower engagement
• Sentiment analysis revealed mostly positive feedback, with recurring concerns related to scheduling, session length, and logistics
• Interactivity and clear structure strongly influence student satisfaction

---

✅ Recommendations

Based on the analysis, the following improvements are suggested:

• Increase interactive and hands-on event formats
• Improve time management and scheduling
• Enhance venue and audio arrangements
• Collect structured feedback consistently after every event
• Use high-performing events as benchmarks for future planning

---

📁 Files in This Repository

• College_Event_Feedback_Analysis_Task3.ipynb
  → Complete Google Colab notebook with analysis and visualizations
• student_feedback.csv
  → Dataset used for the project
• College_Event_Feedback_Analysis_Dashboard.pdf
  → Mini report & dashboard summarizing key insights and recommendations

---

🧾 Deliverables

• ✔ Clean and well-documented analysis notebook
• ✔ Mini report/dashboard with visual insights
• ✔ Actionable recommendations for event organizers

---

👤 Author

Lipika Parida
Data Science & Analytics Intern
Future Interns

---

🔗 Note

Detailed analysis, code, and visualizations are available in the accompanying Google Colab notebook.