Book-Genre-Prediction

KO | EN

gitlite — search

#python #hacktoberfest #llm #go #rust #macos #nodejs #awesome #kubernetes #security #mcp #ios #openai #open-source

Book-Genre-Prediction

(★ 10)

The aim of this project is to apply the principles of text mining on a piece of literary text, and categorize it into the genre into which it best fits.

Book-Genre-Prediction Latest Version Download

Download Latest Version (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Book Genre Prediction using Book Summary

### The aim of the project is to apply the principles of text mining on a piece of literary text and categorize it into the genre into which it best fits.

IPython Notebook has been used for this project.

- The dataset used here is a subset of the CMU Book Summary Dataset available at [CMU Book Summary Dataset](http://www.cs.cmu.edu/~dbamman/booksummaries.html). The dataset was unevenly distributed at the beginning. After days of data wrangling, we attained some uniformity in the dataset. The processed dataset has been uploaded as BookDataSet.csv, which has 6 main genres - "Crime Fiction", "Fantasy", "Historical novel", "Horror", "Science Fiction", "Thriller".

![Snap of dataset](https://github.com/Sirsho1997/Book-Genre-Prediction-using-Book-Summary/blob/master/image/dataset_snap.png)

- The goal of this repository is to provide an example for performing Text Classification using the techniques of Natural Language Processing.

- The highest accuracy was obtained during an 85-15% split while using an SVM with Radial Basis Function as the kernel function. The highest accuracy is 79.55%.

- Required Libraries
    - [Pandas](https://pandas.pydata.org/)
    - [NumPy](https://numpy.org/)
    - [Scikit-Learn](https://scikit-learn.org/stable/)
    - [Matplotlib](https://matplotlib.org/)
    - [Seaborn](https://seaborn.pydata.org/)
    - [NLTK](https://www.nltk.org/)

### For viewing the whole code - [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Sirsho1997/Book-Genre-Prediction-using-Book-Summary/blob/master/BookGenrePrediction.ipynb)

##### Data pre-processing

- Let us have a look at the "summary" column.

- Preprocessing the "summary" column and making it ready for prediction.

- At first, the "summary" is traversed, and only the alphabets are kept while filtering out everything else. Then the alphabets are converted into lowercase.

- Visualizing words and their frequency in the "summary".

- Removing stop words.

Another part of data cleaning is the removal of stop words – that is, common words like “the”, “a”, “an”. They are assumed to have no consequence over the classification process.

- Lemmatization

In lemmatization, the different versions of the same word are put into one – for example, “do/doing/does/did”, “go/going/goes/went” – so as to not let the algorithm treat similar words as different, and hence, make the analysis stronger.

- Stemming

Stemming is the process of producing morphological variants of the root/base word. Stemming reduces the words “chocolates”, “chocolatey”, “choco” to the root word, “chocolate” and “retrieval”, “retrieved”, “retrieves” reduce to the stem “retrieve”.

- Visualizing the words in the book's summary after successfully pre-processing.

- Finally, tf-idf is performed on the dataset. This numerical statistic reflects how a word is important in a document.

Tf_Idf(t,d,D) = tf(t,d).idf(t,D)

Where,
    Tf(t,d) = ft,d
    Idf(t,D) = log(N/{d∈D : t ∈ d})
  With,
    ft,d: Frequency of the term t in document d.
    N: Total number of documents.
    {d∈D : t ∈ d}: Number of documents where the term t appears.

##### Models

**1. At first, an 80-20% split was performed on the dataset**

- Logistic Regression is used when the dependent variable (target) is categorical. Logistic regressions are only binary classifiers, meaning they cannot handle target vectors with more than two classes. However, there are clever extensions to logistic regression to do just that. In one-vs-rest logistic regression (OVR), a separate model is trained for each class predicted whether an observation is that class or not (thus making it a binary classification problem). It assumes that each classification problem (e.g. class 0 or not) is independent.

- SVMs try to find a separating line (or hyperplane) between data of two classes. SVM is an algorithm that takes the data as an input and outputs a line that separates those classes if possible. According to the SVM algorithm, we find the points closest to the line from both classes. These points are called support vectors. Now, we compute the distance between the line and the support vectors. This distance is called the margin. Our goal is to maximize the margin. The hyperplane for which the margin is maximum is the optimal hyperplane. Thus, SVM tries to make a decision boundary in such a way that the separation between the two classes (that street) is as wide as possible. The linear, polynomial, and RBF or Gaussian kernel are simply different in case of making the hyperplane decision boundary between the classes. The kernel functions are used to map the original dataset (linear/nonlinear) into a higher dimensional space with a view to making it a linear dataset. Usually, linear and polynomial kernels are less time-consuming and provide less accuracy than the RBF or Gaussian kernels.

**SVM - Linear**

**SVM - RBF**

**2. Next, an 85-15% split was performed on the dataset**

**Logistic Regression**

**SVM - Linear**

**SVM - RBF**

- Thus, we conclude that the **highest accuracy** was obtained during an **85-15%** split while using an **SVM with RBF as the kernel function**.

- The highest **accuracy is 79.55%**

- Now, we build an **inference function for predicting the genres of new books in the future.**

- Our book genre prediction system should be able to take a book's summary in raw form as input and generate its genre tag.

- Sample output:

![Snap of Final output](https://github.com/Sirsho1997/Book-Genre-Prediction-using-Book-Summary/blob/master/image/sample_op.png)

Team Members:
- Aniket Patra [Github](https://github.com/KamadoTanjiro-beep/)
- [Sirshendu Ganguly](https://www.linkedin.com/in/sirshendu-ganguly/) [![Github](https://github.com/Sirsho1997/Book-Genre-Prediction-using-Book-Summary/blob/master/image/github.png)](https://github.com/Sirsho1997)
- [Arnanta Chatterjee](https://www.linkedin.com/in/arnanta-chatterjee-a60684179/) [![Github](https://github.com/Sirsho1997/Book-Genre-Prediction-using-Book-Summary/blob/master/image/github.png)](https://github.com/arnanta)

Book-Genre-Prediction

Book-Genre-Prediction Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

Book-Genre-Prediction

Book-Genre-Prediction Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

Download README