How to select and weight context dimensions conditions for context-aware recommendation?

Zammali, Saloua; Yahia, Sadok Ben

doi:10.1016/j.eswa.2021.115176

Cited by 4 publications

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Li et al [21] provided a statistical solution for the multidimensional problem in the context-aware recommendation approaches by using random forest algorithm to select and weight the contextual factors. The contextual factors weighting can be achieved by several optimization algorithms such as Particle Swarm Optimisation (PSO) or the gradient descent optimization [22] with an error correction using a fitness function such as Mean Square Error (MSE) or Root Mean Square Error (RMSE) [22], [23]. But some of the reviewed approaches opted out the factors' selection process and only weighs all available factors which results in less personalized recommendations [24], [25].…”

Section: B Context Representation and Contextual Factors Extractionmentioning

confidence: 99%

Contextual and Sentimental Teachers’ Peer Recommendations

Nashed

Lahoud

Abel

2022

2022 IEEE 25th International Conference on Computer Supported Cooperative Work in Design (CSCWD)

View full text Add to dashboard Cite

The current recommender systems' approaches favor item's recommendation over peer's recommendation. Such virtual information systems do not allow face-to-face communication for collaborative knowledge exchange between peers. However, the on-going worldwide situation affects the sentimental state and especially for a teacher who struggle to adapt his course's contents according to current variables. These challenges can be mitigated through personalized peer recommendations for teachers. A more-experienced teacher can provide the required support for a less-experienced one in the form of knowledge sharing. This paper proposes a matching approach to provide peer recommendations for teachers in consonance with their context and sentimental state. The peer recommendation aids the teacher to collaborate with other teachers in the form of experience sharing and knowledge sharing. Furthermore, the paper highlights the similarity measurement criteria for contextual and sentimental matching algorithm in addition to predefined rules. At the end, the paper discusses the effectiveness of the algorithm application with a real-life scenario.

show abstract