Goal

Create an interactive dashboard that analyzes text sentiment (positive/negative/neutral) from:

✔ User input
✔ Tweets
✔ Reviews
✔ Uploaded CSV files

Displays visual charts (pie chart, bar chart, timeline).

---

🧠 What the Project Will Do

The dashboard can:

✔ Accept text input
✔ Analyze sentiment in real-time
✔ Upload a CSV of comments
✔ Process each comment using NLP
✔ Show counts of Positive, Neutral, Negative
✔ Show sentiment distribution graph
✔ Show average sentiment score
✔ Show word cloud (optional)

---

🧰 Tech Stack

• Python
• TextBlob / NLTK / Transformers
• Streamlit (dashboard)
• Matplotlib / Plotly
• Pandas

---

📁 Folder Structure

SentimentDashboard/
│── app.py
│── requirements.txt
│── sample_reviews.csv

---

📦 requirements.txt

streamlit
pandas
textblob
matplotlib
wordcloud

Install all:

pip install -r requirements.txt

or manually:

pip install streamlit textblob pandas matplotlib wordcloud
python -m textblob.download_corpora

---

🧩 Full Working Sentiment Dashboard Code (app.py)

import streamlit as st
import pandas as pd
from textblob import TextBlob
import matplotlib.pyplot as plt

st.title("Sentiment Analysis Dashboard")
st.write("Analyze text sentiment in real-time")

def analyze_sentiment(text):
    score = TextBlob(text).sentiment.polarity
    if score > 0:
        return "Positive", score
    elif score < 0:
        return "Negative", score
    else:
        return "Neutral", score

# --- Option 1: Single Text Input ---
st.header("Single Text Sentiment")
user_text = st.text_area("Enter text")

if st.button("Analyze"):
    sentiment, score = analyze_sentiment(user_text)
    st.success(f"Sentiment: {sentiment} (Score: {score})")

# --- Option 2: CSV Upload ---
st.header("CSV Sentiment Analysis")
file = st.file_uploader("Upload CSV with 'text' column", type=['csv'])

if file is not None:
    df = pd.read_csv(file)
    df["Sentiment"] = df["text"].apply(lambda x: analyze_sentiment(x)[0])
    df["Score"] = df["text"].apply(lambda x: analyze_sentiment(x)[1])
    st.write(df)

    # Count sentiment values
    counts = df["Sentiment"].value_counts()

    # Plot
    st.subheader("Sentiment Distribution")
    fig, ax = plt.subplots()
    ax.pie(counts, labels=counts.index, autopct="%1.1f%%")
    st.pyplot(fig)

---

▶ Run the Dashboard

streamlit run app.py

Opens in browser:

http://localhost:8501

---

📊 Features in Dashboard

1. Sentiment Analyzer

• Positive
• Negative
• Neutral
• Shows sentiment score (-1 to +1)

2. CSV Analysis

Upload file like:

text
"Great product"
"Very bad service"
"Okay, not good not bad"

Dashboard shows:

• Table with sentiment
• Pie chart
• Score distribution

3. Graphs

Optional additions:

⭐ Bar chart
⭐ Word cloud
⭐ Sentiment over time