Search results

Community question answering (CQA) platforms play a significant role in knowledge dissemination and information retrieval. Expert recommendation can assist users by helping them find valuable answers efficiently. Existing works mainly use content and user behavioural features for expert recommendation, and fail to effectively leverage the correlation across multi-dimensional features.

To address the above issue, this work proposes a multi-dimensional feature fusion-based method for expert recommendation, aiming to integrate features of question–answerer pairs from three dimensions, including network features, content features and user behaviour features. Specifically, network features are extracted by first learning user and tag representations using network representation learning methods and then calculating questioner–answerer similarities and answerer–tag similarities. Secondly, content features are extracted from textual contents of questions and answerer generated contents using text representation models. Thirdly, user behaviour features are extracted from user actions observed in CQA platforms, such as following and likes. Finally, given a question–answerer pair, the three dimensional features are fused and used to predict the probability of the candidate expert answering the given question.

The proposed method is evaluated on a data set collected from a publicly available CQA platform. Results show that the proposed method is effective compared with baseline methods. Ablation study shows that network features is the most important dimensional features among all three dimensional features.

This work identifies three dimensional features for expert recommendation in CQA platforms and conducts a comprehensive investigation into the importance of features for the performance of expert recommendation. The results suggest that network features are the most important features among three-dimensional features, which indicates that the performance of expert recommendation in CQA platforms is likely to get improved by further mining network features using advanced techniques, such as graph neural networks. One broader implication is that it is always important to include multi-dimensional features for expert recommendation and conduct systematic investigation to identify the most important features for finding directions for improvement.

This work proposes three-dimensional features given that existing works mostly focus on one or two-dimensional features and demonstrate the effectiveness of the newly proposed features.

Coronavirus disease 2019 (COVID-19) has made telecommuting widely valued, but different individuals have different degrees of acceptance of telecommuting. This article aims to identify suitable individuals for telework and to clarify which types of workers are suitable for what level of telework, set scientific, reasonable hybrid work ratios and processes and measure their suitability.

First, two working scenarios of different risk levels were established, and the theory of planned behavior (TPB) was used to introduce latent variables, constructing a multi-indicator multi-causal model (MIMIC) to identify suitable individuals, and second, constructing an integrated choice and latent variable (ICLV) model of the working method to determine the suitability of different types of people for telework by calculating their selection probabilities.

It is possible to clearly distinguish between two types of suitable individuals for telework or traditional work. Their behavior is significantly influenced by the work environment, which is influenced by variables such as age, income, attitude, perceived behavioral control, work–family balance and personnel exposure level. In low-risk scenarios, the influencing factors of the behavioral model for both types of people are relatively consistent, while in high-risk scenarios, significant differences arise. Furthermore, the suitability of telework for the telework-suitable group is less affected by the pandemic, while the suitability for the non-suitable group is greatly affected.

This study contributes to previous literature by: (1) determining the suitability of different population types for telework by calculating the probability of selection, (2) dividing telework and traditional populations into two categories, identifying the differences in factors that affect telework under different epidemic risks and (3) considering the impact of changes in the work scenario on the suitability of telework for employees and classifying the population based on the suitability of telework in order to avoid the potential negative impact of telework.