Learning Representations for Soft Skill Matching

Abstract

Employers actively look for talents having not only specific hard skills but also various soft skills. To analyze the soft skill demands on the job market, it is important to be able to detect soft skill phrases from job advertisements automatically. However, a naive matching of soft skill phrases can lead to false positive matches when a soft skill phrase, such as friendly, is used to describe a company, a team, or another entity, rather than a desired candidate. In this paper, we propose a phrase-matching-based approach which differentiates between soft skill phrases referring to a candidate vs. something else. The disambiguation is formulated as a binary text classification problem where the prediction is made for the potential soft skill based on the context where it occurs. To inform the model about the soft skill for which the prediction is made, we develop several approaches, including soft skill masking and soft skill tagging. We compare several neural network based approaches, including CNN, LSTM and Hierarchical Attention Model. The proposed tagging-based input representation using LSTM achieved the highest recall of 83.92% on the job dataset when fixing a precision to 95%.

A Survey on Skill Identification From Online Job Ads

“…It is one of the fundamental tasks in NLP with broad applications such as sentiment analysis and spam detection. It was applied by [44], [45] to classify sentences that contain skills in the job ad description. The authors labeled a huge dataset containing sentences of job ads.…”

“…Sifting such sentences can help in accurately identifying skills within job ads and prevent false extracted skills. In [44], the authors compared Convolutional Neural Network (CNN) and LSTM models for sentence classification. CNN model allows taking into account the word order by applying a fixed-size window on the input array composed of words and their corresponding word embedding dimensions [58].…”

“…Therefore, some researchers have taken a further step by detecting sentences containing the skill term as a first step, where deep learning models were used to label job description sentences. For instance, [44], [45] identifies the sentences containing the soft skills and hard skills consecutively, then skills are identified as n-grams from a predefined skill base or list of skills.…”

“…Sector specific [15], [21], [22], [39], [40], [62], [63], [66] Soft and Hard skills Sector specific [69], [125] Soft and Hard skills All sectors [33], [47], [64] Soft skills Sector specific Job ads and Resumes [26] Soft and Hard skills All sectors [44] Soft skills sentences All sectors [27] Soft and Hard skills All sectors [25] soft and Hard skills All sectors Job ads and Interviews [34] Soft and Hard skills Sector specific LinkedIn resumes [32] Soft and Hard skills All sectors Curricula development job ads [68] soft and hard skills sector specific [67] Soft and hard skills Sector specific Job ads and University programs [89] Hard skills Sector specific…”

What skills do IT companies look for in new developers? A study with Stack Overflow jobs

“…By contrast, other skills denote behavioral characteristics of the candidates, such as verbal communication, team player, leadership, etc. They are known as soft skills [3]. In this article, we analyze both hard and soft skills required by IT job opportunities.…”