Learn practical skills, build real-world projects, and advance your career

Fake Job Posting Analysis

Introduction

With the increase of data, there is an increase in false information as well such as fake news, job scams, false advertising and so on. Since finding a job through online job postings was a real challenge for me, I decided to analyze job postings and find out differences between real and fake ones.

The dataset, [Real or Fake] : Fake Job Description Prediction, was retrieved from website Kaggle, which is originally from Laboratory of Information & Communication Systems Security of University of the Aegean (Greece). This is a public dataset of 17,880 real-life job ads where there are 17,014 legitimate and 866 fraudulent job ads published between 2012 and 2014. Dataset consists of 17,880 rows and 18 columns.

Downloading the Dataset

Let's download dataset directly from Kaggle website by using dataset's url. This way, there is no need to download csv file and upload it back to Jupyter.

!pip install jovian opendatasets --upgrade --quiet

We'll begin by downloading the data, and listing the files within the dataset.

dataset_url = 'https://www.kaggle.com/shivamb/real-or-fake-fake-jobposting-prediction'