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.

本文采用双向 LSTM 模型结合数字和文本特征鉴别虚假的招聘广告，取得了 0.91 的 ROC AUC 和 98.71% 的准确率，展现了在在线招聘市场中广泛应用的潜力。研究结果为开发实用工具以及应对网络招聘诈骗提供了借鉴，同时探讨了所采用方法的挑战，未来研究方向和伦理道德方面的考虑。

使用双向 LSTM 检测虚假工作职位

Detecting Fake Job Postings Using Bidirectional LSTM

Skills play a central role in the job market and many human resources (HR)
processes. In the wake of other digital experiences, today's online job market
has candidates expecting to see the right opportunities based on their skill
set. Similarly, enterprises increasingly need to use data to guarantee that the
skills within their workforce remain future-proof. However, structured
information about skills is often missing, and processes building on self- or
manager-assessment have shown to struggle with issues around adoption,
completeness, and freshness of the resulting data. Extracting skills is a
highly challenging task, given the many thousands of possible skill labels
mentioned either explicitly or merely described implicitly and the lack of
finely annotated training corpora. Previous work on skill extraction overly
simplifies the task to an explicit entity detection task or builds on manually
annotated training data that would be infeasible if applied to a complete
vocabulary of skills. We propose an end-to-end system for skill extraction,
based on distant supervision through literal matching. We propose and evaluate
several negative sampling strategies, tuned on a small validation dataset, to
improve the generalization of skill extraction towards implicitly mentioned
skills, despite the lack of such implicit skills in the distantly supervised
data. We observe that using the ESCO taxonomy to select negative examples from
related skills yields the biggest improvements, and combining three different
strategies in one model further increases the performance, up to 8 percentage
points in RP@5. We introduce a manually annotated evaluation benchmark for
skill extraction based on the ESCO taxonomy, on which we validate our models.
We release the benchmark dataset for research purposes to stimulate further
research on the task.

本研究提出了一种基于远程监督的技能提取系统，结合 ESCO 分类法和多种负采样策略提高提取技能的性能，并引入手动注释的基准评估数据集，以促进该任务的进一步研究。