Combining content-based and collaborative filtering for job recommendation system: A cost-sensitive Statistical Relational Learning approach

Yang, Shuo; Korayem, Mohammed; AlJadda, Khalifeh; Grainger, Trey; Natarajan, Sriraam

doi:10.1016/j.knosys.2017.08.017

Cited by 112 publications

(43 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods show the actual interest a user has and help predict what they might want to do at any given time. It accurately indicates the users' interest [20]. This system conditionally adapts to the likes and dislikes of the users through its adaptive filtering.…”

Section: Content-basedmentioning

confidence: 99%

Trust-Based Collaborative Filtering Recommendation Systems on the Blockchain

Yeh¹,

Kashef²

2020

AIT

View full text Add to dashboard Cite

A blockchain is a digitized, decentralized, public ledger of all cryptocurrency transactions. The blockchain is transforming industries by enabling innovative business practices. Its revolutionary power has permeated areas such as banking, financing, trading, manufacturing, supply chain management, healthcare, and government. Blockchain and the Internet of Things (BIOT) apply the usage of blockchain in the inter-IOT communication system, therefore, security and privacy factors are achievable. The integration of blockchain technology and IoT creates modern decentralized systems. The BIOT models can be applied by various industries including e-commerce to promote decentralization, scalability, and security. This research calls for innovative and advanced research on Blockchain and recommendation systems. We aim at building a secure and trust-based system using the advantages of blockchain-supported secure multiparty computation by adding smart contracts with the main blockchain protocol. Combining the recommendation systems and blockchain technology allows online activities to be more secure and private. A system is constructed for enterprises to collaboratively create a secure database and host a steadily updated model using smart contract systems. Learning case studies include a model to recommend movies to users. The accuracy of models is evaluated by an incentive mechanism that offers a fully trust-based recommendation system with acceptable performance.

show abstract

Section: Content-basedmentioning

confidence: 99%

Trust-Based Collaborative Filtering Recommendation Systems on the Blockchain

Yeh¹,

Kashef²

2020

AIT

View full text Add to dashboard Cite

show abstract

“…The Puntheeranurak and Chaiwitooanukool have used items attributes similarities and later use these similarities to adjust the values of the predicted ratings [13]. Statistical Relational Learning can be used for a hybrid approach by using the probabilistic dependencies among the attributes [14]. A news utility model was developed to address the problem of considering clicks as the most effective indicator of real user interests by most of all the existing recommendation system…”

Section: Related Workmentioning

confidence: 99%

Generating Quality Items Recommendation by Fusing Content based and Collaborative filtering

2019

IJITEE

View full text Add to dashboard Cite

Recommendation system has become an inevitable part of our life. It has already spread its prominence in various fields like movies, music, news, article recommendations etc. Due to the influence of social media, data is streaming from all over the Internet. Collect the relevant information from chunks of data available has become much difficult. Recommender systems guides in filtering data to get the relevant information. Commonly used recommendation approaches are content based filtering and collaborative filtering. Each approach has its own limitations. The hybrid approach combines the advantages of both the approaches. In this paper, we have tried to enhance the quality of the items recommendation system by fusing both content based and collaborative filtering uniquely. The experimental results are compared with that of other traditional approach using precision and recall evaluation measure. The comparison results show that our approach has 10% better precision for top-10 recommendations than other established recommendation technique.

show abstract

“…Diaby et al [3] proposed a computational model that suggests jobs to different online social media users from their available profiles. In a recent work, the authors propose a hybrid approach [17] that leverages the strengths of both CF and content based filtering for job recommendation. Lu et al [11] have built recommendation systems for job seeking and recruiting websites, in which traditional content based, relational based, and a hybrid model are used for computing a similarity value between a job and a candidate; then personalized multi-relational page rank is used for ranking the jobs in terms of preference of a candidate.…”

Section: Related Workmentioning

confidence: 99%

A Combined Representation Learning Approach for Better Job and Skill Recommendation

Dave

Zhang

Hasan

et al. 2018

Proceedings of the 27th ACM International Conference on Information and Knowledge Management

Self Cite

View full text Add to dashboard Cite

Job recommendation is an important task for the modern recruitment industry. An excellent job recommender system not only enables to recommend a higher paying job which is maximally aligned with the skill-set of the current job, but also suggests to acquire few additional skills which are required to assume the new position. In this work, we created three types of information networks from the historical job data: (i) job transition network, (ii) job-skill network, and (iii) skill co-occurrence network. We provide a representation learning model which can utilize the information from all three networks to jointly learn the representation of the jobs and skills in the shared k-dimensional latent space. In our experiments, we show that by jointly learning the representation for the jobs and skills, our model provides better recommendation for both jobs and skills. Additionally, we also show some case studies which validate our claims.

show abstract

Combining content-based and collaborative filtering for job recommendation system: A cost-sensitive Statistical Relational Learning approach

Cited by 112 publications

References 16 publications

Trust-Based Collaborative Filtering Recommendation Systems on the Blockchain

Trust-Based Collaborative Filtering Recommendation Systems on the Blockchain

Generating Quality Items Recommendation by Fusing Content based and Collaborative filtering

A Combined Representation Learning Approach for Better Job and Skill Recommendation

Contact Info

Product

Resources

About