Link prediction in knowledge graph is the task of utilizing the existing relations to infer new relations so as to build a more complete knowledge graph. The inferred new relations plus original knowledge graph is the symmetry of completion knowledge graph. Previous research on link predication only focuses on path or semantic-based features, which can hardly have a full insight of features between entities and may result in a certain ratio of false inference results. To improve the accuracy of link predication, we propose a novel approach named Entity Link Prediction for Knowledge Graph (ELPKG), which can achieve a high accuracy on large-scale knowledge graphs while keeping desirable efficiency. ELPKG first combines path and semantic-based features together to represent the relationships between entities. Then it adopts a probabilistic soft logic-based reasoning method that effectively solves the problem of non-deterministic knowledge reasoning. Finally, the relation between entities is completed based on the entity link prediction algorithm. Extensive experiments on real dataset show that ELPKG outperforms baseline methods on hits@1, hits@10, and MRR.

Existing methods for monitoring internet public opinion rely primarily on regular crawling of textual information on web pages but cannot quickly and accurately acquire and identify textual information in images and videos and discriminate sentiment. The problems make this a challenging research point for multimodal information detection in an internet public opinion scenario. In this paper, we look at how to dynamically monitor the internet opinion information (mostly images and videos) that different websites post. Based on the most recent advancements in text recognition, this paper proposes a new method of visual multimodal text recognition and sentiment analysis (MTR-SAM) for internet public opinion analysis scenarios. In the detection module, a LK-PAN network with large sensory fields is proposed to enhance the CML distillation strategy, and an RSE-FPN with a residual attention mechanism is used to improve feature map representation. Second, it proposes that the original CTC decoder be replaced with a GTC method to solve earlier problems with text detection at arbitrary rotation angles. Additionally, the performance of scene text detection for arbitrary rotation angles is improved using a sinusoidal loss function for rotation recognition. Finally, the improved sentiment analysis model is used to predict the sentiment polarity of the text recognition results. The experimental results show that the new method proposed in this paper improves recognition speed by 31.77%, recognition accuracy by 10.78% on the video dataset, and the F1 score of the multimodal sentiment analysis model by 4.42% on the self-built internet public opinion dataset (lab dataset). The method proposed provides significant technical support for internet public opinion analysis in multimodal domains.

Weakly supervised anomalous behavior detection is a popular area at present. Compared to semi-supervised anomalous behavior detection, weakly-supervised learning both eliminates the need to crop videos and solves the problem of semi-supervised learning’s difficulty in handling long videos. Previous work has used graph convolution or self-attention mechanisms to model temporal relationships. However, these methods tend to model temporal relationships at a single scale and lack consideration of the aggregation problem for different temporal relationships. In this paper, we propose a weakly supervised anomaly detection framework, MTDA-Net, with emphasis on modeling different temporal relationships and enhanced semantic discrimination. To this end, we construct a new plug-and-play module, MTDA, which uses three branches, Multi-headed Attention (MHA), Temporal Shift (TS), and Dilated Aggregation (DA), to extract different temporal sequences. Specifically, the MHA branch can globally model the video information and project the features into different semantic spaces to enhance the expressiveness and discrimination of the features. The DA branch extracts temporal information of different scales via dilated convolution and captures the temporal features of local regions in the video. The TS branch can fuse the features of adjacent frames on a local scale and enhance the information flow. MTDA-Net can learn the temporal relationships between video segments on different branches and learn powerful video representations based on these relationships. The experimental results on the XD-Violence dataset show that MTDA-Net can significantly improve the detection accuracy of abnormal behaviors.

Knowledge graph conflict resolution is a method to solve the knowledge conflict problem in constructing knowledge graphs. The existing methods ignore the time attributes of facts and the dynamic changes of the relationships between entities in knowledge graphs, which is liable to cause high error rates in dynamic knowledge graph construction. In this article, we propose a knowledge graph conflict resolution method, knowledge graph evolution algorithm based on deep learning (Kgedl), which can resolve facts confliction with high precision by combing time attributes, semantic embedding representations, and graph structure features. Kgedl first trains the semantic embedding vector through the relationships between entities. Then, the path embedding vector is trained from the graph structures of knowledge graphs, and the time attributes of entities are combined with the semantic and path embedding vectors. Finally, Kgedl uses a recurrent neural network to make the inconsistent facts appear in the dynamic evolution of the knowledge graph consistent. A large number of experiments on real datasets show that Kgedl outperforms the state-of-the-art methods. Especially, Kgedl achieves 23% higher performance than the classical method numerical Probabilistic Soft Logic (nPSL).in the metric HITS@10. Also, extensive experiments verified that our proposal possess better robustness by adding noise data.

Geolocating Twitter users from social media data holds significant value in applications such as targeted advertising, disaster response, and social network analysis. However, existing social network-based geolocation methods tend to focus primarily on mention relations while neglecting other critical interactions like retweet relationships. Moreover, effectively integrating diverse social features remains a key challenge, which limits the overall performance of geolocation models. To address these issues, this paper proposes a novel Twitter user geolocation method based on multi-graph feature fusion with a gating mechanism, termed MGFGCN, which fully leverages heterogeneous social network information. Specifically, MGFGCN first constructs separate mention and retweet graphs to capture multi-dimensional user relationships. It then incorporates the Information Gain Ratio (IGR) to select discriminative keywords and generates Term Frequency–Inverse Document Frequency (TF-IDF) features, thereby enhancing the semantic representation of user nodes. Furthermore, to exploit complementary information across different graph structures, we propose a Structure-aware Gated Fusion Mechanism (SGFM) that dynamically captures differences and interactions between nodes from each graph, enabling the effective fusion of node representations into a unified representation for subsequent location inference. Experimental results demonstrate that the proposed method outperforms existing state-of-the-art baselines in the Twitter user geolocation task across two public datasets.