# IntelliWeb

**Repository Path**: chenfei11113/IntelliWeb

## Basic Information

- **Project Name**: IntelliWeb
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2020-12-27
- **Last Updated**: 2020-12-27

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# IntelliWeb
IntelliWeb is a novel method of web page classification based on Natural Language Processing of web page content. This project solves web classification with multiple methods:
* Baseline classifier 1 : Naive Bayes - TF-IDF vectors
* Baseline classifier 2 : Support Vector Machine - TF-IDF vectors
* IntelliWeb : Deep Neural Network with Long Short-term Memory cells - GloVe vectors

IntelliWeb is designed on [LSTM](https://www.mitpressjournals.org/doi/10.1162/neco.1997.9.8.1735) with [GloVe](https://nlp.stanford.edu/projects/glove/) embeddings. Following softwares are required to run this code.

Softwares | Versions
--- | ---
Python | v3.6
Numpy| v1.15.4
Pandas | v0.23.4
Scikit-learn | v20.0
NLTK | v3.3
BeautifulSoup | 4.6.3
matplotlib | v3.0.1
Keras | 2.2.4
TensorFlow | 1.11.0
GloVe | v1.2


## Report
You can find a detailed report [here.](./reports/P08_webpageclassification_deeplearning.pdf)