SAO2Vec: Development of an algorithm for embedding the subject-action-object (SAO) structure using Doc2Vec

Multimodal Feature Fusion Based Hypergraph Learning Model

Hypergraph learning is a new research hotspot in the machine learning field. The performance of the hypergraph learning model depends on the quality of the hypergraph structure built by different feature extraction methods as well as its incidence matrix. However, the existing models are all hypergraph structures built based on one feature extraction method, with limited feature extraction and abstract expression ability. This paper proposed a multimodal feature fusion method, which firstly built a single modal hypergraph structure based on different feature extraction methods, and then extended the hypergraph incidence matrix and weight matrix of different modals. The extended matrices fuse the multimodal abstract feature and an expanded Markov random walk range during model learning, with stronger feature expression ability. However, the extended multimodal incidence matrix has a high scale and high computational cost. Therefore, the Laplacian matrix fusion method was proposed, which performed Laplacian matrix transformation on the incidence matrix and weight matrix of every model, respectively, and then conducted a weighted superposition on these Laplacian matrices for subsequent model training. The tests on four different types of datasets indicate that the hypergraph learning model obtained after multimodal feature fusion has a better classification performance than the single modal model. After Laplace matrix fusion, the average time can be reduced by about 40% compared with the extended incidence matrix, the classification performance can be further improved, and the index F1 can be improved by 8.4%.

Long-Term City Innovation Trajectories and Quality of Urban Life

The main aims of this paper are to examine the technological trajectories of city innovation, to provide a picture of the current state in the most significant technologies, and to propose an explanation for the long-run evolutionary trajectories of technological developments that contribute to the quality of urban life through innovation. In the conceptual part of the paper, we develop the argument that the explanation may rest on the interrelationships between the concept of urban transformative capacity and the theory of path dependence. In the empirical part, we analyze patent data on city-related innovations to examine the trajectories of technological developments over the period 1980–2020. Our main findings at a technological field level (i) confirm the path dependence theory in general and the institutional approach in particular, (ii) acknowledge the rapid transformation towards ‘smart cities’ through the explosive growth of digital technologies, and (iii) confirm the environmental sustainability concerns when developing new technologies. In our study, we focus particularly on the technological sectors (‘clusters’) that provide a significant contribution to quality of urban life, namely environment, public services, and leisure and participation. Our findings provide theoretical, managerial, and policy implications for future research activities on the technological developments that benefit quality of urban life.