Purpose The purpose of this paper is to provide a cross-platform recommendation system that recommends the most suitable public Instagram accounts to Facebook users. Design/methodology/approach We collect data from both Facebook and Instagram and then propose a similarity matching mechanism for recommending the most appropriate Instagram accounts to Facebook users. By removing the data disparity between the two heterogeneous platforms and integrating them, the system is able to make more accurate recommendations. Findings The results show that the method proposed in this paper can recommend suitable public Instagram accounts to Facebook users with very high accuracy. Originality/value To the best of the authors’ knowledge, this is the first study to propose a recommender system to recommend Instagram public accounts to Facebook users. Second, our proposed method can integrate heterogeneous data from two different platforms to generate collaborative recommendations. Furthermore, our cross-platform system reveals an innovative concept of how multiple platforms can promote their respective platforms in a unified, cooperative and collaborative manner.

In this study, a computer program DBFWD is developed for data analysis of Falling Weight Deflectometer (FWD) test on flexible pavements. To backcalculate the layer moduli of the pavement, a number of iterative backcalculation schemes were employed with the forward analysis of the Green's flexibility influence functions. The temperature and the moisture influences on material moduli of the asphalt surface and the subgrade soils were considered in the analysis. As the result, the iterative scheme based on the peak deflection ratios was selected to backcalculate the layer moduli of local pavements. Owing to the correction procedure used in the program, interpretations with four original deflections were found more accurate than those with equivalent number of modified deflections. Comparisons of program DBFWD with other static backcalculation programs on theoretical and experimental deflections indicated that dynamic interpretation is more effective in providing the layer modulus information. Despite of the requirements of accurate inputs of the layer thickness and the testing load for the analysis, a generalized application of the program needs to be clarified with model road test in demand.