Personality detection from text is commonly performed by analysing users' social media posts. However, existing methods heavily rely on large-scale annotated datasets, making it challenging to obtain high-quality personality labels. Moreover, most studies treat emotion and personality as independent variables, overlooking their interactions. In this paper, we propose a novel self-supervised framework, EmoPerso, which improves personality detection through emotion-aware modelling. EmoPerso first leverages generative mechanisms for synthetic data augmentation and rich representation learning. It then extracts pseudo-labeled emotion features and jointly optimizes them with personality prediction via multi-task learning. A cross-attention module is employed to capture fine-grained interactions between personality traits and the inferred emotional representations. To further refine relational reasoning, EmoPerso adopts a self-taught strategy to enhance the model's reasoning capabilities iteratively. Extensive experiments on two benchmark datasets demonstrate that EmoPerso surpasses state-of-the-art models. The source code is available at https://github.com/slz0925/EmoPerso.

Graph-based personality detection constructs graph structures from textual data, particularly social media posts. Current methods often struggle with sparse or noisy data and rely on static graphs, limiting their ability to capture dynamic changes between nodes and relationships. This paper introduces LL4G, a self-supervised framework leveraging large language models (LLMs) to optimize graph neural networks (GNNs). LLMs extract rich semantic features to generate node representations and to infer explicit and implicit relationships. The graph structure adaptively adds nodes and edges based on input data, continuously optimizing itself. The GNN then uses these optimized representations for joint training on node reconstruction, edge prediction, and contrastive learning tasks. This integration of semantic and structural information generates robust personality profiles. Experimental results on Kaggle and Pandora datasets show LL4G outperforms state-of-the-art models.

Personality detection automatically identifies an individual’s personality from various data sources, such as social media texts. However, as the parameter scale of language models continues to grow, the computational cost becomes increasingly difficult to manage. Fine-tuning also grows more complex, making it harder to justify the effort and reliably predict outcomes. We introduce a novel parameter-efficient fine-tuning framework, PersLLM, to address these challenges. In PersLLM, a large language model (LLM) extracts high-dimensional representations from raw data and stores them in a dynamic memory layer. PersLLM then updates the downstream layers with a replaceable output network, enabling flexible adaptation to various personality detection scenarios. By storing the features in the memory layer, we eliminate the need for repeated complex computations by the LLM. Meanwhile, the lightweight output network serves as a proxy for evaluating the overall effectiveness of the framework, improving the predictability of results. Experimental results on key benchmark datasets like Kaggle and Pandora show that PersLLM significantly reduces computational cost while maintaining competitive performance and strong adaptability.

Cultural awareness in language models is the capacity to understand and adapt to diverse cultural contexts. However, most existing approaches treat culture as static background knowledge, overlooking its dynamic and evolving nature. This limitation reduces their reliability in downstream tasks that demand genuine cultural sensitivity. In this work, we introduce CALM, a novel framework designed to endow language models with cultural self-awareness. CALM disentangles task semantics from explicit cultural concepts and latent cultural signals, shaping them into structured cultural clusters through contrastive learning. These clusters are then aligned via cross-attention to establish fine-grained interactions among related cultural features and are adaptively integrated through a Mixture-of-Experts mechanism along culture-specific dimensions. The resulting unified representation is fused with the model's original knowledge to construct a culturally grounded internal identity state, which is further enhanced through self-prompted reflective learning, enabling continual adaptation and self-correction. Extensive experiments conducted on multiple cross-cultural benchmark datasets demonstrate that CALM consistently outperforms state-of-the-art methods.

Multimodal fake news detection often involves modelling heterogeneous data sources, such as vision and language. Existing detection methods typically rely on fusion effectiveness and cross-modal consistency to model the content, complicating understanding how each modality affects prediction accuracy. Additionally, these methods are primarily based on static feature modelling, making it difficult to adapt to the dynamic changes and relationships between different data modalities. This paper develops a significantly novel approach, GAMED, for multimodal modelling, which focuses on generating distinctive and discriminative features through modal decoupling to enhance cross-modal synergies, thereby optimizing overall performance in the detection process. GAMED leverages multiple parallel expert networks to refine features and pre-embed semantic knowledge to improve the experts' ability in information selection and viewpoint sharing. Subsequently, the feature distribution of each modality is adaptively adjusted based on the respective experts' opinions. GAMED also introduces a novel classification technique to dynamically manage contributions from different modalities, while improving the explainability of decisions. Experimental results on the Fakeddit and Yang datasets demonstrate that GAMED performs better than recently developed state-of-the-art models. The source code can be accessed at https://github.com/slz0925/GAMED.

Graph neural networks (GNNs) become popular in recommender systems treating the interaction data of user and item as a bipartite graph. Recently, graph contrastive learning achieves superior results for collaborative filtering by reinforcing the learned representations by generating contrastive views through data augmentation. Despite their successful application in recommendation scenarios, there is still some room for improvement: most of these methods perform data augmentation from the data perspective, and the model potential is not exploited enough because more contrastive perspectives are not considered; negative sample bias caused by the different degrees of nodes exists in the contrastive loss. In this paper, we propose a Siamese Adaptive Contrastive learning framework (SACL) to mitigate these issues. Our model utilizes Siamese network as a small perturbation to the model and combines it with data augmentation to learn more robust representations and realizes adaptive contrastive learning introducing the common neighbors’ information of users and items to weight negative samples. Experiments on several public datasets show better performance of our model compared to existing representative methods.

Collaborative Filtering (CF) models based on Graph Contrastive Learning (GCL) have effectively improved the performance of long-tail recommendation. However, the popularity bias still presents a challenge in further enhancing their effectiveness. Some studies suggest that achieving better recommendations, particularly for the long-tail, requires learning representations with a more uniform distribution to implicitly mitigate popularity bias. Nevertheless, our analysis of various CF models reveals that different models exhibit varying abilities in capturing popularity and those with superior performance might encode more popularity information in item representations. This raises a question: Does encoding popularity always lead to harmful bias? We speculate that superior recommendations may emerge from leveraging the encoded popularity information to optimize the representations of users and items rather than eliminating its existence in representations. This motivates a data augmentation approach, wherein we generate augmented samples by mixing representations of items with different popularity levels and explicitly debias using the encoded popularity information which is often neglected. Additionally, we propose an adaptive contrastive loss, leveraging structural information and unifying the recommendation and contrastive learning objectives, which adaptively re-weights positive samples and ensures the capture of item popularity. Our proposed framework remains scalable without requiring multiple forward computations throughout the entire graph. Extensive experiments demonstrate improvements in both overall and long-tail recommendation performance.

Collaborative filtering (CF) is the basic method for recommendation with implicit feedback. Recently, various state-of-the-art CF integrates graph neural networks. However, they often suffer from popularity bias, causing recommendations to deviate from users' genuine preferences. Additionally, several contrastive learning methods based on the in-batch sample strategy have been proposed to train the CF model effectively, but they are prone to suffering from sample bias. To address this problem, debiased contrastive loss has been employed in the recommendation, but instead of personalized debiasing, it treats each user equally. In this paper, we propose a popularity-aware debiased contrastive loss for CF, which can adaptively correct the positive and negative scores based on the popularity of users and items. Our approach aims to reduce the negative impact of popularity and sample bias simultaneously. We theoretically analyze the effectiveness of the proposed method and reveal the relationship between popularity and gradient, which justifies the correction strategy. We extensively evaluate our method on three public benchmarks over balanced and imbalanced settings. The results demonstrate its superiority over the existing debiased strategies, not only on the entire datasets but also when segmenting the datasets based on item popularity.

Master tutors are important guides in the academic career of postgraduate students, so find and choose a suitable tutor is very important. However, the existing master tutor selection mode has many problems such as information asymmetry, which makes it difficult for students to make the most appropriate choice. With the construction of smart campus, more and more educational data are recorded, which makes it possible to conduct Educational Data Mining. In this paper, master tutors and students were respectively modeled, a master tutor recommendation method based on machine learning algorithms, such as TF-IDF, kNN and SVDCF was introduced. A real data set of our university was built and preprocessed. Specific recommendation algorithms were then designed. Experiments were conducted and acceptable Top-N hit rate results were achieved. The experimental results show that based on the modeling of students and master tutors, a lightweight combination of machine learning algorithms can achieve good practical results.