We propose a DeiT (Data-Efficient Image Transformer) feature encoder-based algorithm for identifying disease types and generating relevant descriptions of diseased crops. It solves the scarcity problem of the image description algorithm applied in agriculture. We divided the original image into a sequence of image patches to fit the input form of the DeiT encoder, which was distilled by RegNet. Then, we used the Transformer decoder to generate descriptions. Compared to “CNN + LSTM” models, our proposed model is entirely convolution-free and has high training efficiency. On the Rice2k dataset created by us, the model achieved a 47.3 BLEU-4 score, 65.0 ROUGE_L score, and 177.1 CIDEr score. The extensive experiments demonstrate the effectiveness and the strong robustness of our model. It can be better applied to automatically generate descriptions of similar crop disease characteristics.

Based on employees’ online reviews, this article analyzes the dimensions of job demand for new-generation employees, using a combination model of Latent Dirichlet Allocation, decision-making trials and evaluation laboratory, interpretative structural modeling, and cross-impact matrix multiplication (LDA—DEMATEL—ISM—MICMAC). The results show that job demand is composed of 10 dimensions, and there is significant interdependence between the dimensions. Changing one dimension will quickly affect the other dimensions. The dimension with the greatest influence degree is leadership and team atmosphere (s₁), while the dimension with the highest affected degree and centrality degree is welfare and promotion (s₃). Leadership and team atmosphere (s₁), company culture and industry (s₄), overall environment and platform (s₅), and platform and technology (s₇) were identified as the key factors. They play a causal role in job demand and have a significant impact on other dimensions. Dimensions such as working relationship and intensity (s₂), welfare and promotion (s₃), opportunity and resources (s₆), business and industry development (s₈), corporate prospects and personal development (s₉), and work stress and position (s₁₀) are affected by other dimensions and require special attention. The underlying need is present for the dimension of leadership and team atmosphere (s₁), which has a direct or indirect impact on other dimensions in different ways.

Student Evaluation of Teaching (SET) provides both quantitative ratings and open-ended textual feedback for assessing teaching quality, yet these two information sources are often analyzed separately. This study investigates whether numerical ratings and textual evaluations provide fully aligned information and how their relationship varies across teaching contexts. Using 42,724 cleaned evaluation records from a university in China, including 44,713 sub-comments for sentiment inference and a final analytical sample of 1342 instructors, we develop an artificial intelligence-driven educational data mining framework that integrates Latent Dirichlet Allocation (LDA) topic modeling with RoBERTa-based sentiment analysis. LDA is used to identify latent pedagogical themes, while RoBERTa estimates continuous sentiment scores from textual comments. To support joint analysis of the two modalities, we further define the Score–Emotion Deviation (D) as an applied operational measure of the numerical discrepancy between normalized evaluation scores and model-derived sentiment scores. The empirical analysis shows that numerical ratings and textual sentiment are highly concentrated near their upper ranges but nevertheless exhibit localized score–text discrepancies. The distributions of the operational deviation measure also vary across academic titles, disciplines, and class sizes. By combining thematic, sentiment, and numerical-rating information within a unified analytical framework, this study extends multimodal educational data mining for SET analysis and provides complementary evidence that can support more contextualized diagnosis and interpretation of teaching quality.