# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!

cff-version: 1.2.0
title: >-
  Semantic Duplicate Detection: Quora Question Pairs
  Analysis using Machine Learning
message: >-
  If you use this software, please cite it using the
  metadata from this file.
type: software
authors:
  - given-names: Fahad
    family-names: Deshmukh
    email: deshmukh@uni-potsdam.de
    affiliation: University of Potsdam
identifiers:
  - type: url
    value: 'https://github.com/fahaddeshmukh/Question-pair-nlp'
    description: github repo
abstract: >-

  This project presents a machine learning (ML)-based
  solution for the Quora Question Pairs challenge hosted on
  Kaggle. With a focus on natural language processing (NLP),
  the project addresses the task of identifying whether
  pairs of questions from the Quora platform are duplicates.
  The primary objective is to construct binary
  classification models capable of determining whether two
  provided questions are semantically similar or represent
  duplicates.


  The project involves a dataset comprising over 400,000
  observations across six columns: 'ID', 'QID1', 'QID2',
  'Question1', 'Question2', and 'Is_duplicate'. Through
  systematic processing, exploratory data analysis, and
  feature engineering, the project seeks to derive insights
  for model development. The 'Is_duplicate' column,
  containing boolean values indicating question duplicity,
  serves as the dependent variable.


  The project encompasses loading and preprocessing the
  dataset, conducting exploratory data analysis, and
  performing feature engineering using NLP techniques. The
  engineered features are then subjected to additional
  exploratory analysis. Predictive modeling forms the
  culminating phase of the project, where various binary
  classification models are trained and evaluated to
  determine the most effective solution.


  By addressing the Quora Question Pairs challenge, this
  project contributes to the field of NLP and
  classification, demonstrating the application of machine
  learning techniques in detecting semantic similarity
  within textual data. The outcomes shed light on the
  efficacy of different models and feature engineering
  strategies in tackling real-world NLP tasks.
keywords:
  - NLP
  - Machine Learning
  - Python
  - jupyter notebbok
  - Semantic duplicate
license: MIT
date-released: '2023-08-10'