pages/Introduction.py

import streamlit as st
from facts import show_fun_fact

st.set_page_config(layout="centered")

st.markdown("""

    <h1 style='text-align: center; color: white;'>Introduction to NLP! (Natural Language Processing)</h1>

    <h3 style='text-align: center; color: white;'>A powerful library for working with text data</h3>

""", unsafe_allow_html=True)

# What is NLP?
st.markdown("## What is NLP? 🤖")
st.markdown("""

**Natural Language**: Refers to human languages like English, Spanish, etc. In NLP, we focus on understanding and processing these languages.



**Processing**: This refers to the steps or techniques we use to handle the text, such as breaking it down into smaller units, removing noise, and extracting meaningful information.



**NLP (Natural Language Processing)**: The combination of the above two. It's a technology that allows machines to understand, interpret, and interact with human language.



In simpler terms:

- **Human Language**: Words, sentences, and meaning.

- **Processing**: Techniques to analyze and manipulate these words to get useful insights.

""")




st.markdown("## How Is NLP Used? 🤔")
st.markdown("""

NLP helps in tasks like:

- **Text Classification**: Automatically grouping text into categories (e.g., email spam detection).

- **Sentiment Analysis**: Understanding the mood or emotion behind a text (e.g., is the review positive or negative?).

- **Named Entity Recognition (NER)**: Identifying specific items in text, such as names of people, places, or dates.

- **Document Summarization**: Creating a short version of a longer text, keeping only the key points.

- **Language Translation**: Converting text from one language to another automatically.

            

Thus, NLP is all about enabling computers to understand and process text, which can be used for a wide range of applications, from chatbots to translation services.

""")
            
            
# Key Features of NLP
st.markdown("## Key Features of NLP 🔧")
st.markdown("""

Some of the main features provided by NLP libraries (like `spaCy`, `NLTK`, `TextBlob`, etc.) include:



- **Tokenization**: Breaking text into words or sentences.

- **Part-of-Speech Tagging (POS)**: Identifying the **Part of Speech** category of each word (e.g., noun, verb, adjective).

- **Stemming and Lemmatization**: Reducing words to their base form to standardize text (e.g., "running" to "run").

- **Vectorization**: Converting text into numerical formats (e.g., TF-IDF, Word2Vec) for machine learning models to process.



These features are essential for processing and understanding textual data efficiently.

""")

# Real-World Applications
st.markdown("## Real-World Applications of NLP 🌍")
st.markdown("""

NLP is widely used for various text data processing tasks across industries. Some key applications include:



- **Customer Feedback Analysis**

- **Document Categorization**

- **Chatbots and Virtual Assistants**

- **Social Media Sentiment Analysis**

- **Search Engine Optimization**



NLP is applicable in almost every field that works with textual data.

""")

st.markdown("""

## Why is NLP Important?❗""")
st.markdown("""

NLP is essential because it enables machines to understand, interpret, and respond to human language in ways that are useful across various domains. With the vast amount of text data generated daily, NLP becomes necessary for:



- **Automating Text-based Tasks**: From chatbots to automating document classification.

- **Improving Human-Computer Interaction**: Virtual assistants like Siri, and Alexa rely on NLP to process and respond to voice commands.

- **Breaking Language Barriers**: NLP powers translation tools like Google Translate.

- **Enhancing Search Engines**: Better search results through understanding queries.



As digital communication continues to grow, NLP is increasingly required to make sense of unstructured text data and to facilitate smoother interactions between humans and machines.

""")

show_fun_fact()