Taking Chengdu as an example, based on the destination image theory and employing the content analysis methodology, this paper conducts data mining on the online comment texts of TikTok short food videos, and analyzes the impact of short food videos on the destination image (cognitive image, affective image and conative image). The results show that: (1) in terms of cognitive image, short food videos have increased potential tourists’ attention to the destination image, especially their attention to the flavor characteristics of food in the destination and the local social environment; (2) in terms of affective image, the comments of short food videos are mainly neutral and positive, and the contents about the flavor characteristics of food and the local social environment are more likely to affect the affective image of the destination; and (3) in terms of conative image, the appearance description of food in short food videos brings about an obvious effect of intention, and it also creates the demand to travel together and obtain information. This paper is inspiring for city managers and tourism marketers to use TikTok short videos to establish and disseminate food-based city brands and destination images.

No abstract

No abstract

Differentially expressed genes selection becomes a hotspot and difficulty in recent molecular biology. Low-rank representation (LRR) uniting graph Laplacian regularization has gained good achievement in the above field. However, the co-expression information of data cannot be captured well by graph regularization. Therefore, a novel low-rank representation method regularized by dual-hypergraph Laplacian is proposed to reveal the intrinsic geometrical structures hidden in the samples and genes direction simultaneously, which is called dual-hypergraph Laplacian regularized LRR (DHLRR). Finally, a low-rank matrix and a sparse perturbation matrix can be recovered from genomic data by DHLRR. Based on the sparsity of differentially expressed genes, the sparse disturbance matrix can be applied to extracting differentially expressed genes. In our experiments, two gene analysis tools are used to discuss the experimental results. The results on two real genomic data and an integrated dataset prove that DHLRR is efficient and effective in finding differentially expressed genes.

No abstract