Salience and Market-aware Skill Extraction for Job Targeting

At LinkedIn, we want to create economic opportunity for everyone in the global workforce. To make this happen, LinkedIn offers a reactive Job Search system, and a proactive Jobs You May Be Interested In (JYMBII) system to match the best candidates with their dream jobs. One of the most challenging tasks for developing these systems is to properly extract important skill entities from job postings and then target members with matched attributes. In this work, we show that the commonly used text-based salience and market-agnostic skill extraction approach is sub-optimal because it only considers skill mention and ignores the salient level of a skill and its market dynamics, i.e., the market supply and demand influence on the importance of skills. To address the above drawbacks, we present Job2Skills, our deployed salience and market-aware skill extraction system. The proposed Job2Skills shows promising results in improving the online performance of job recommendation (JYMBII) (+1.92% job apply) and skill suggestions for job posters (-37% suggestion rejection rate). Lastly, we present case studies to show interesting insights that contrast traditional skill recognition method and the proposed Job2Skills from occupation, industry, country, and individual skill levels. Based on the above promising results, we deployed the Job2Skills online to extract job targeting skills for all 20M job postings served at LinkedIn.

[1]  Kirk P. Arnett,et al.  IT skills in a tough job market , 2005, Commun. ACM.

[2]  Bo Zhao,et al.  Learning Global Term Weights for Content-based Recommender Systems , 2016, WWW.

[3]  Jia Li,et al.  How to Get Them a Dream Job?: Entity-Aware Features for Personalized Job Search Ranking , 2016, KDD.

[4]  Enhong Chen,et al.  Trend-Aware Tensor Factorization for Job Skill Demand Analysis , 2019, IJCAI.

[5]  Shan Li,et al.  Deep Job Understanding at LinkedIn , 2020, SIGIR.

[6]  Deepak Agarwal,et al.  GLMix: Generalized Linear Mixed Models For Large-Scale Response Prediction , 2016, KDD.

[7]  Yiqun Liu,et al.  How Integration helps on Cold-Start Recommendations , 2017, RecSys 2017.

[8]  Hui Xiong,et al.  Enhancing Person-Job Fit for Talent Recruitment: An Ability-aware Neural Network Approach , 2018, SIGIR.

[9]  Tim Weninger,et al.  Representation Learning in Heterogeneous Professional Social Networks with Ambiguous Social Connections , 2019, 2019 IEEE International Conference on Big Data (Big Data).

[10]  Maksims Volkovs,et al.  Content-based Neighbor Models for Cold Start in Recommender Systems , 2017, RecSys 2017.

[11]  Charlie Wang,et al.  Estimating skill fungibility and forecasting services labor demand , 2017, 2017 IEEE International Conference on Big Data (Big Data).

[12]  Shan Li,et al.  Learning to Ask Screening Questions for Job Postings , 2020, SIGIR.

[13]  Chuan Qin,et al.  DuerQuiz: A Personalized Question Recommender System for Intelligent Job Interview , 2019, KDD.

[14]  Aristides Gionis,et al.  Machine learned job recommendation , 2011, RecSys '11.

[15]  Tomas Mikolov,et al.  Enriching Word Vectors with Subword Information , 2016, TACL.

[16]  Satoshi Sekine,et al.  A survey of named entity recognition and classification , 2007 .

[17]  Qing He,et al.  The Impact of Person-Organization Fit on Talent Management: A Structure-Aware Convolutional Neural Network Approach , 2019, KDD.

[18]  Nan Hua,et al.  Universal Sentence Encoder , 2018, ArXiv.

[19]  Hui Xiong,et al.  Measuring the Popularity of Job Skills in Recruitment Market: A Multi-Criteria Approach , 2017, AAAI.

[20]  Dean Knudson,et al.  Investigating the skill gap between graduating students and industry expectations , 2014, ICSE Companion.

[21]  Chao Huang,et al.  Multiplex Behavioral Relation Learning for Recommendation via Memory Augmented Transformer Network , 2020, SIGIR.

[22]  Fabian Abel,et al.  RecSys Challenge 2017: Offline and Online Evaluation , 2017, RecSys.

[23]  Moninder Singh,et al.  Estimating Fungibility Between Skills by Combining Skill Similarities Obtained from Multiple Data Sources , 2017, Data Science and Engineering.

[24]  Tat-Seng Chua,et al.  Neural Collaborative Filtering , 2017, WWW.

[25]  Bo Hu,et al.  Towards Deep and Representation Learning for Talent Search at LinkedIn , 2018, CIKM.

[26]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[27]  Yin Lou,et al.  BDT: Gradient Boosted Decision Tables for High Accuracy and Scoring Efficiency , 2017, KDD.

[28]  Lin Zhu,et al.  Social Skill Validation at LinkedIn , 2019, KDD.

[29]  Heng-Tze Cheng,et al.  Wide & Deep Learning for Recommender Systems , 2016, DLRS@RecSys.

[30]  Ganesh Venkataraman,et al.  Personalized Job Recommendation System at LinkedIn: Practical Challenges and Lessons Learned , 2017, RecSys.

[31]  Fabian Abel.  We Know Where You Should Work Next Summer: Job Recommendations , 2015, RecSys.

[32]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[33]  Deepak Agarwal,et al.  Spatio-temporal models for estimating click-through rate , 2009, WWW '09.

[34]  E. Saar,et al.  Participation in job-related training in European countries: the impact of skill supply and demand characteristics , 2017 .

[35]  Tong Xu,et al.  Identifying High Potential Talent: A Neural Network Based Dynamic Social Profiling Approach , 2019, 2019 IEEE International Conference on Data Mining (ICDM).

[36]  Vachik S. Dave,et al.  A Combined Representation Learning Approach for Better Job and Skill Recommendation , 2018, CIKM.

[37]  Hui Xiong,et al.  Person-Job Fit , 2018, ACM Trans. Manag. Inf. Syst..

[38]  Le Zhang,et al.  A Hierarchical Career-Path-Aware Neural Network for Job Mobility Prediction , 2019, KDD.

[39]  Nitesh V. Chawla,et al.  Online Purchase Prediction via Multi-Scale Modeling of Behavior Dynamics , 2019, KDD.

[40]  Liang Zhang,et al.  LiJAR: A System for Job Application Redistribution towards Efficient Career Marketplace , 2017, KDD.

[41]  Qi He,et al.  NEMO: Next Career Move Prediction with Contextual Embedding , 2017, WWW.

[42]  Michael D. Mumford,et al.  UNDERSTANDING WORK USING THE OCCUPATIONAL INFORMATION NETWORK (O*NET): IMPLICATIONS FOR PRACTICE AND RESEARCH , 2001 .

[43]  Wei Lee Woon,et al.  Changes in Occupational Skills - A Case Study Using Non-negative Matrix Factorization , 2015, ICONIP.