Personality detection aims to deduce a user’s personality from their published posts. The goal of this task is to map posts to specific personality types. Existing methods encode post information to obtain user vectors, which are then mapped to personality labels. However, existing methods face two main issues: first, only using small models makes it hard to accurately extract semantic features from multiple long documents. Second, the relationship between user vectors and personality labels is not fully considered. To address the issue of poor user representation, we utilize the text embedding capabilities of LLM. To solve the problem of insufficient consideration of the relationship between user vectors and personality labels, we leverage the text generation capabilities of LLM. Therefore, we propose the LLM-Enhanced Text Mapping Model (ETM) for Personality Detection. The model applies LLM’s text embedding capability to enhance user vector representations. Additionally, it uses LLM’s text generation capability to create multi-perspective interpretations of the labels, which are then used within a contrastive learning framework to strengthen the mapping of these vectors to personality labels. Experimental results show that our model achieves state-of-the-art performance on benchmark datasets.

Community structure refers to the “small groups” in the network. Detecting community structure in networks has significant application value. With the continuous expansion and complexity of the network, the global information of the network is often difficult to obtain. On the other hand, in some cases, we pay more attention to the local community where the given node is located. Local community detection methods detect local community structure by using local information from a given node. However, many local community detection methods encounter the problem of precision limitation. Therefore, in order to alleviate such problems, we propose the FG-based method in this paper. Based on the characteristics of complex networks, a folded subgraph method is designed to consider some similar nodes as single nodes, reducing the impact of noise in the network. Furthermore, based on the folded subgraph, FG-based method designs a three-stage local expansion strategy, in which nodes with different characteristics are added to the local community in each stage. We conduct experiments on datasets and find that the FG-based method can improve the recall and precision of local community structures.

The number of jellyfish outbreaks is on the rise around the world, and they have been considered a serious ecological disaster. As part of the emergency response plan for jellyfish disasters, in-situ detection research that can distinguish jellyfish species and quantities is urgently required to support accurate data collection. As a typical fully supervised regression task, counting is usually regarded as requiring a large number of labeled datasets in conventional counting methods. To treat counting as a few-shot regression task that is semi-supervised, a novel adaptation strategy based on deep learning is presented in this paper. The method combines the test image with several example objects from the test image and takes advantage of the strong similarities present in the test image and the example objects contained in the image. Effective counting can be achieved without training the target object. Prediction of the density map of the test image’s objects of interest is the objective of the test. This method has been shown to be more robust than the method of detection first and counting later, and its accuracy can exceed 95%.