CARIA : A Personalized Career Recommender Based on Individual Competency Similarity Measure

被引:0
|
作者
Seesukong, Supaluck [1 ]
Angskun, Thara [1 ]
Keandoungchun, Nantapong [2 ]
Thippongtorn, Atitthan [3 ]
Angskun, Jitimon [1 ]
机构
[1] Suranaree Univ Technol, Inst Digital Arts & Sci, Nakhon Ratchasima, Thailand
[2] King Mongkuts Univ Technol, Sch Informat Technol, Thonburi, Thailand
[3] Suranaree Univ Technol Hosp, Chai Mongkhon, Thailand
关键词
Career Recommender; Digital Career; Individual Competency; Similarity Measures; STUDENTS; SYSTEM;
D O I
10.4018/IJICTE.356499
中图分类号
G40 [教育学];
学科分类号
040101 ; 120403 ;
摘要
The purpose of this research is to create a personalized system called CARIA that suggests career recommendations based on students' competencies and the required skills in each career. The focus of this study is on digital technology and digital media careers. The personalized career recommender system uses a novel similarity measure called modified Euclidean similarity to evaluate its performance and compare it with other similarity measures, machine learning, and GPT-4 techniques. The experimental results showed that modified Euclidean similarity achieved a precision@10 score of 0.83, which outperformed other techniques. The main objective of CARIA is to provide students with suitable career paths and conduct a competency gap analysis. This helps students choose a career path that fits their abilities. This research contributes to education in digital technology, digital media, and the workforce by providing employees with competencies that align with their needs.
引用
收藏
页数:24
相关论文
共 50 条
  • [31] Personalized recommender system based on social relations
    Ebrahimi, Fahimeh
    Golpayegani, S. Alireza Hashemi
    2016 24TH IRANIAN CONFERENCE ON ELECTRICAL ENGINEERING (ICEE), 2016, : 218 - 223
  • [32] A Personalized Recommender System Based on a Hybrid Model
    Hussein, Wedad
    Ismail, Rasha M.
    Gharib, Tarek F.
    Mostafa, Mostafa G. M.
    JOURNAL OF UNIVERSAL COMPUTER SCIENCE, 2013, 19 (15) : 2224 - 2240
  • [33] Combining Algorithms and User Experience: A Hybrid Personalized Movie Recommender Based on Perceived Similarity Completed Research Paper
    Li, Jingjing
    AMCIS 2013 PROCEEDINGS, 2013,
  • [34] A sub-one quasi-norm-based similarity measure for collaborative filtering in recommender systems
    Jiang, Shan
    Fang, Shu-Cherng
    An, Qi
    Lavery, John E.
    INFORMATION SCIENCES, 2019, 487 : 142 - 155
  • [35] Similarity based Matrix Factorization for Recommender Systems
    Zhang, Gen
    Zhou, Xu
    2017 10TH INTERNATIONAL SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE AND DESIGN (ISCID), VOL. 1, 2017, : 7 - 11
  • [36] The Application of Competency Based on Unascertained Measure
    Ma Jibin
    Zheng Baoqing
    PROCEEDINGS OF THE FIRST INTERNATIONAL WORKSHOP ON EDUCATION TECHNOLOGY AND COMPUTER SCIENCE, VOL I, 2009, : 560 - +
  • [37] MFSR: A novel multi-level fuzzy similarity measure for recommender systems
    Shojaei, Mansoore
    Saneifar, Hassan
    EXPERT SYSTEMS WITH APPLICATIONS, 2021, 177
  • [38] Proposed similarity measure using Bhattacharyya coefficient for context aware recommender system
    Dixit, Veer Sain
    Jain, Parul
    JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2019, 36 (04) : 3105 - 3117
  • [39] An Efficient Similarity Measure for User-Based Collaborative Filtering Recommender Systems Inspired by the Physical Resonance Principle
    Tan, Zhenhua
    He, Liangliang
    IEEE ACCESS, 2017, 5 : 27211 - 27228
  • [40] The Adaptive Ontology-Based Personalized Recommender System
    Cheng, Sheng-Tzong
    Chou, Chih-Lun
    Horng, Gwo-Jiun
    WIRELESS PERSONAL COMMUNICATIONS, 2013, 72 (04) : 1801 - 1826