e-ISSN: 2582-5208 International Research Journal of Modernization in Engineering Technology and Science ( Peer-Reviewed, Open Access, Fully Refereed International Journal ) Volume:05/Issue:03/March-2023 Impact Factor- 7.868 www.irjmets.com www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science [3883] DETECTING FAKE JOB POSTINGS USING BIDIRECTIONAL LSTM Aravind Sasidharan Pillai *1 *1 The University Of Illinois, Urbana-Champaign, IL, USA. DOI : https://www.doi.org/10.56726/IRJMETS35202 ABSTRACT Fake job postings have become prevalent in the online job market, posing significant challenges to job seekers and employers. Despite the growing need to address this problem, there is limited research that leverages deep learning techniques for the detection of fraudulent job advertisements. This study aims to fill the gap by employing a Bidirectional Long Short-Term Memory (Bi-LSTM) model to identify fake job advertisements. Our approach considers both numeric and text features, effectively capturing the underlying patterns and relationships within the data. The proposed model demonstrates a superior performance, achieving a 0.91 ROC AUC score and a 98.71% accuracy rate, indicating its potential for practical applications in the online job market. The findings of this research contribute to the development of robust, automated tools that can help combat the proliferation of fake job postings and improve the overall integrity of the job search process. Moreover, we discuss challenges, future research directions, and ethical considerations related to our approach, aiming to inspire further exploration and development of practical solutions to combat online job fraud. Keywords: Data Science, Deep Learning, Machine Learning, Fake Job Posting Detection. I. INTRODUCTION The rapid growth of the internet has transformed the way job seekers and employers interact, with online job portals becoming a vital resource for millions of people worldwide. However, while these platforms offer numerous benefits, they have also raised a significant problem: the proliferation of fake job postings. Fraudulent job advertisements waste job seekers' time and resources, posing severe risks such as identity theft and financial loss. Therefore, effective methods are needed to detect and mitigate the impact of fake job postings. Machine learning and NLP techniques have shown great promise in detecting deceptive content across various domains, including spam email detection, fake news identification, and sentiment analysis. In this context, Recurrent Neural Networks (RNNs) and their variants, such as Long Short-Term Memory (LSTM) networks, have emerged as powerful tools for processing sequential data and capturing the temporal patterns in text. Furthermore, Bidirectional LSTM (Bi-LSTM) networks have demonstrated remarkable performance in various NLP tasks, as they can learn and process contextual information from past and future time steps. This paper proposes a novel approach to detecting fake job postings using Bidirectional LSTM networks. We hypothesize that the ability of Bi-LSTM to capture the complex structure of textual data effectively can be harnessed to distinguish between genuine and fraudulent job advertisements. We present a comprehensive methodology, including text preprocessing, word embedding, and model training, and evaluate our proposed model on various datasets. Finally, through a series of experiments, we demonstrate the efficacy of our approach and compare its performance with other state-of-the-art techniques, ultimately showcasing the potential of Bidirectional LSTM in addressing the growing issue of fake job postings. II. METHODOLOGY This section presents the methodology for detecting fake job postings using Bidirectional LSTM networks. Our approach comprises several key stages, including literature reviews, data analysis and preprocessing, and word embedding. 2.1 Literature Review Detecting fake job postings is closely related to the broader field of deceptive content detection. In this section, we review several critical studies and techniques employed in detecting misleading content, including spam, fake news, and online reviews, as well as previous attempts to identify fake job postings. Spam emails often contain fraudulent content and deceptive language. Researchers have developed various machine-learning algorithms to detect and filter spam emails. For example, Sahami et al. (1998)[1] proposed