Download as PDF, PPTX
![Research Questions
4
[RQ1] Does enabling job seekers to interact with
visualization techniques empower them to explore,
understand, and find job recommendations?
[RQ2] Do personal characteristics, such as age and
background, impact the user perception and user
interaction with such an interface?](https://image.slidesharecdn.com/recsys19-final-20190916-190916143059/75/Explaining-and-Exploring-Job-Recommendations-a-User-driven-Approach-for-Interacting-with-Knowledge-based-Job-Recommender-Systems-4-2048.jpg)
![Labor Market Explorer design goals
10
[DG1] Exploration/Control
Job seekers should be able to control
recommendations and filter out the information
flow coming from the recommender engine by
prioritizing specific items of interest.
[DG2] Explanations
Recommendations and matching scores should be
explained, and details should be provided on-
demand.
[DG3] Actionable Insights
The interface should provide actionable insights to
help job-seekers find new or more job
recommendations from different perspectives.](https://image.slidesharecdn.com/recsys19-final-20190916-190916143059/75/Explaining-and-Exploring-Job-Recommendations-a-User-driven-Approach-for-Interacting-with-Knowledge-based-Job-Recommender-Systems-10-2048.jpg)
![[DG1] Exploration/Control
11](https://image.slidesharecdn.com/recsys19-final-20190916-190916143059/75/Explaining-and-Exploring-Job-Recommendations-a-User-driven-Approach-for-Interacting-with-Knowledge-based-Job-Recommender-Systems-11-2048.jpg)
![[DG2] Explanations
12](https://image.slidesharecdn.com/recsys19-final-20190916-190916143059/75/Explaining-and-Exploring-Job-Recommendations-a-User-driven-Approach-for-Interacting-with-Knowledge-based-Job-Recommender-Systems-12-2048.jpg)
![[DG3] Actionable insights
13](https://image.slidesharecdn.com/recsys19-final-20190916-190916143059/75/Explaining-and-Exploring-Job-Recommendations-a-User-driven-Approach-for-Interacting-with-Knowledge-based-Job-Recommender-Systems-13-2048.jpg)
![Discussion
[RQ1] User Empowerment
• The approach is perceived as effective to explore job recommendations.
• Most participants felt confident and will use the explorer again.
• Explanations contribute to support user empowerment.
• A diverse set of actionable insights were also mentioned by participants.
21](https://image.slidesharecdn.com/recsys19-final-20190916-190916143059/75/Explaining-and-Exploring-Job-Recommendations-a-User-driven-Approach-for-Interacting-with-Knowledge-based-Job-Recommender-Systems-21-2048.jpg)
![[RQ2] Personal Characteristics
• The explorer was slightly better perceived by older participants (45+).
• Participants in the technical group engaged more with all the different
features of the dashboard.
• Non-native speakers, sales and construction groups engaged more
with the map.
• The table overview was perceived as very useful by all user groups, but
the interaction may need further simplification for some users.
Discussion
22](https://image.slidesharecdn.com/recsys19-final-20190916-190916143059/75/Explaining-and-Exploring-Job-Recommendations-a-User-driven-Approach-for-Interacting-with-Knowledge-based-Job-Recommender-Systems-22-2048.jpg)
Uploaded byKatrien Verbert
Explaining and Exploring Job Recommendations: a User-driven Approach for Interacting with Knowledge-based Job Recommender Systems
This document describes a user-driven approach for interacting with a knowledge-based job recommender system called the Labor Market Explorer. The Explorer was designed based on a user-centered process to provide job seekers with explanations of recommendations, exploration and control over diverse recommendations, and actionable insights. An evaluation with 66 job seekers found that the Explorer effectively empowered users to explore recommendations. Personal characteristics like age and background impacted how users interacted with the interface. The design process and key features of the Explorer could inform future job recommendation systems.
More Related Content
Similar to Explaining and Exploring Job Recommendations: a User-driven Approach for Interacting with Knowledge-based Job Recommender Systems
Explaining and Exploring Job Recommendations: a User-driven Approach for Interacting with Knowledge-based Job Recommender Systems
- 1. Explaining and ExploringJob Recommendations: a User-driven Approach for Interacting with Knowledge-based Job Recommender Systems Francisco Gutiérrez, Sven Charleer, Robin De Croon, Nyi Nyi Htun, Gerd Goetschalckx, Katrien Verbert Computer Science Department, KU Leuven http://augment.cs.kuleuven.be [email protected] @FranciscoGhz 1 [email protected] @katrien_v AUGMENT
- 2. 22 • Abundant overloadof job vacancies • Dynamic Labor Market: need to support job mobility • Providing effective recommendations particularly challenging. • Need for: increased diversity explanations user control exploration Problem: interaction with job RecSys needed
- 3. Explaining job recommendationsto show competence match Support exploration and user control over broad and diverse recommendations Approach
- 4. Research Questions 4 [RQ1] Doesenabling job seekers to interact with visualization techniques empower them to explore, understand, and find job recommendations? [RQ2] Do personal characteristics, such as age and background, impact the user perception and user interaction with such an interface?
- 5. 5 Interactive & JobRecommender Systems SetFusion (Parra et al., 2014) LinkedVis (Bostandjiev, 2013) JobStreet (Bakri et al., 2017)
- 6. Labor Market Explorer Interactivedashboard to support job seekers Explore and explain recommendations - actionable insights
- 7.
- 8. 8 Ranking of parametersas voted by participants
- 9.
- 10. Labor Market Explorerdesign goals 10 [DG1] Exploration/Control Job seekers should be able to control recommendations and filter out the information flow coming from the recommender engine by prioritizing specific items of interest. [DG2] Explanations Recommendations and matching scores should be explained, and details should be provided on- demand. [DG3] Actionable Insights The interface should provide actionable insights to help job-seekers find new or more job recommendations from different perspectives.
- 11.
- 12.
- 13.
- 14. Final evaluation 66 jobseekers (age 33.9 ± 9.5, 18F) 8 training programs, 4 groups, 1 hour. 1 2 3 4 5 6 7 8 ResQue questionnaire + two open questions. Users explored the tool freely. All interactions were logged. 14
- 15.
- 16.
- 17.
- 18.
- 19.
- 20.
- 21. Discussion [RQ1] User Empowerment •The approach is perceived as effective to explore job recommendations. • Most participants felt confident and will use the explorer again. • Explanations contribute to support user empowerment. • A diverse set of actionable insights were also mentioned by participants. 21
- 22. [RQ2] Personal Characteristics •The explorer was slightly better perceived by older participants (45+). • Participants in the technical group engaged more with all the different features of the dashboard. • Non-native speakers, sales and construction groups engaged more with the map. • The table overview was perceived as very useful by all user groups, but the interaction may need further simplification for some users. Discussion 22
- 23. User-centered design processinvolving both job seekers and job mediators Key features: Design implications 23 • Overview first, favorite competences of interest. • Competence-based explanations. • Actionable, job market related insights. • Diverse set of filters.
- 24. • Future workwill focus on a “simulation mode”. • Further investigate job mobility scenarios. • Explore “What-If” scenarios. • Autonomous exploration of the job market. Future work 24
- 25. Explaining and ExploringJob Recommendations: a User-driven Approach for Interacting with Knowledge-based Job Recommender Systems Francisco Gutiérrez, Sven Charleer, Robin De Croon, Nyi Nyi Htun, Gerd Goetschalckx, Katrien Verbert [email protected] @FranciscoGhz 25 [email protected] @katrien_v AUGMENT