Skills prediction based on multi-label resume classification using CNN with model predictions explanation

Jiechieu, Kameni Florentin Flambeau; Tsopzé, Norbert

doi:10.1007/s00521-020-05302-x

Cited by 29 publications

(13 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kameni F. and Al (2020) [12] are interested in the extraction of skills expressed in documents such as CVs or job offers and based on the CNN (convolutional neural network) classification model manage to extract high level skills in CVs with performances reaching 98.79% for recall and 91.34% for precision. However, these data are retrieved in a very formal context.…”

Section: Related Workmentioning

confidence: 99%

Supervised Learning Algorithm on Unstructured Documents for the Classification of Job Offers: Case of Cameroun

Makembe¹,

Etoundi²,

Tapamo³

2023

JCC

View full text Add to dashboard Cite

Nowadays, in data science, supervised learning algorithms are frequently used to perform text classification. However, African textual data, in general, have been studied very little using these methods. This article notes the particularity of the data and measures the level of precision of predictions of naive Bayes algorithms, decision tree, and SVM (Support Vector Machine) on a corpus of computer jobs taken on the internet. This is due to the data imbalance problem in machine learning. However, this problem essentially focuses on the distribution of the number of documents in each class or subclass. Here, we delve deeper into the problem to the word count distribution in a set of documents. The results are compared with those obtained on a set of French IT offers. It appears that the precision of the classification varies between 88% and 90% for French offers against 67%, at most, for Cameroonian offers. The contribution of this study is twofold. Indeed, it clearly shows that, in a similar job category, job offers on the internet in Cameroon are more unstructured compared to those available in France, for example. Moreover, it makes it possible to emit a strong hypothesis according to which sets of texts having a symmetrical distribution of the number of words obtain better results with supervised learning algorithms.

show abstract

Section: Related Workmentioning

confidence: 99%

Supervised Learning Algorithm on Unstructured Documents for the Classification of Job Offers: Case of Cameroun

Makembe¹,

Etoundi²,

Tapamo³

2023

JCC

View full text Add to dashboard Cite

show abstract

“…Recently, several works (Bhola et al, 2020;Jiechieu and Tsopze, 2021) have been done for skill prediction using Extreme Multi-label Classification. XMLC refers to the classification of text where the number of the set of labels is large, i.e., thousands or millions.…”

Section: Background and Related Workmentioning

confidence: 99%

JobXMLC: EXtreme Multi-Label Classification of Job Skills with Graph Neural Networks

Goyal,

Kalra,

Sharma

et al. 2023

Findings of the Association for Computational Linguistics: EACL 2023

View full text Add to dashboard Cite

Writing a good job description is an important step in the online recruitment process to hire the best candidates. Most recruiters forget to include some relevant skills in the job description. These missing skills affect the performance of recruitment tasks such as job suggestions, job search, candidate recommendations, etc. Existing approaches are limited to contextual modelling, do not exploit inter-relational structures like job-job and job-skill relationships, and are not scalable. In this paper, we exploit these structural relationships using a graph-based approach. We propose a novel skill prediction framework called JobXMLC, which uses graph neural networks with skill attention to predict missing skills using job descriptions. JobXMLC enables joint learning over a job-skill graph consisting of 22.8K entities (jobs and skills) and 650K relationships. We experiment with real-world recruitment datasets to evaluate our proposed approach. We train JobXMLC on 20, 298 jobs and 2, 548 skills within 30 minutes on a single GPU machine. JobXMLC outperforms the state-of-the-art approaches by 6% on precision and 3% on recall. JobXMLC is 18X faster for training tasks and up to 634X faster in skill prediction on benchmark datasets enabling JobXMLC to scale up on larger datasets. We have made our code and dataset public at https://precog.iiit.ac.in/resources.html. Job Title Job description Required skills Market Analyst Assist the Manager in sourcing the food industry and in conducting product research and analysis. Facilitate effective communication between the analytics and user experience teams. Evaluates customers' online behaviour and provide insights and recommendations for further enhancements to the guest experience. Strong research, data analysis and communication skills. communication visualization tableau data analysis python Explicit Skills Implicit Skills Excel

show abstract

“…To measure the effectiveness of the pro-posed identification system, they used several important performance metrics such as FAR, DR, and accuracy, and experiments were performed using publicly available datasets, especially the latest heterogeneous dataset CSE-CICIDS2018. The paper [20] In [23] the approach utilized a mixture calculation of convolutional neural network (CNN) and long short term memory (LSTM). The approach is related to further developed interruption identification.…”

Section: Intrusion Detection Systemmentioning

confidence: 99%

Recent Studies and A Review about Malware detection and classification by using Artificial Intelligence Techniques

Abdelhafez,

A. El-Sawy,

Sakr

2023

Benha Journal of Applied Sciences

View full text Add to dashboard Cite

Due to the harmful and unsafe broad utilization of Malware emergency as a result of various sorts of malware, perilous programs, and scripts that are accessible on the tremendous virtual world known as the Web. This study centers on learning around most later different sorts of malware and strategies to induce freed of them by finding them and kicking them out of the framework, which isn't simple since these little pieces of script or code can be found all over within the client framework. In this paper, we highlight malware collection, conglomeration, and dispersal challenges in client framework environment and show a comprehensive dialog on the later ponders that utilized different AI strategies to meet particular destinations of most malware location frameworks, from 2017 to 2022. We compare and differentiate diverse calculations based on optimization criteria, recreation, genuine sending, malware sorts, and execution parameters. We conclude with conceivable future inquire about headings. This would direct the peruser towards an understanding of up-to-date applications of ML methods concerning malware acknowledgment, accumulation, and spread challenges. At that point, we offer a common assessment and comparison of diverse ML strategies used, which is able be a direct for the investigate community in recognizing the foremost adjusted strategies and the benefits of utilizing different AI and machine learning strategies for tackling the challenges related to getting freed of these destructive malware. At long last, we conclude the paper by expressing the open issues of investigate and unused conceivable outcomes for future ponders.

show abstract

Skills prediction based on multi-label resume classification using CNN with model predictions explanation

Cited by 29 publications

References 24 publications

Supervised Learning Algorithm on Unstructured Documents for the Classification of Job Offers: Case of Cameroun

Supervised Learning Algorithm on Unstructured Documents for the Classification of Job Offers: Case of Cameroun

JobXMLC: EXtreme Multi-Label Classification of Job Skills with Graph Neural Networks

Recent Studies and A Review about Malware detection and classification by using Artificial Intelligence Techniques

Contact Info

Product

Resources

About