At present, most news aggregation platforms use personalized recommendation technology to push information in China, which is likely to cause the phenomenon of information cocoons. In order to alleviate the occurrence of this phenomenon, this paper studies the issue of mainstream value information push from different perspectives, which can be used as a supplement for personalized recommendation technology to promote the diffusion of mainstream value information. First, we constructed an evolutionary game model to simulate the game process between news aggregation platforms and users. Through the results of evolutionary analysis, the news platform can be guided at a macro level to formulate mainstream value information push strategies by adjusting model parameters. Second, we conducted research on user behavior, and the results show that different user groups have different demands for mainstream value information. Third, we constructed two models from the perspective of user demands and platform revenue. Experiments show that user sensitivity to mainstream value information $\sigma$ and platform evaluation factors $val$ are important for finding the number of mainstream information pushes on each page. Finally, we investigated the effect of the mainstream value information from Toutiao. The survey results are consistent with the viewpoints presented in this paper.

Online news platforms have become users’ primary information sources. However, they focus on attracting users to click on the news and ignore whether the news triggers a sense of engagement, which could potentially reduce users’ participation in public events. Therefore, this study constructs four indicators by assessing user engagement to build an intelligent system to help platforms optimize their publishing strategies. First, this study defines user engagement evaluation as a classification task that divides user engagement into four indicators and proposes an extended LDA model based on user click–comment behavior (UCCB), using which the attractiveness of words in news headlines and content can be effectively represented. Second, this study proposes a deep user engagement evaluation (DUEE) model that integrates news attractiveness and multiple features in an attention-based deep neural network for user engagement evaluation. The DUEE model considers various elements that collectively determine the ability of the news to attract clicks and engagement. Third, the proposed model is compared with the baseline and state-of-the-art techniques, showing that it outperforms all existing methods. This study provides new research contributions and ideas for improving user engagement in online news evaluation.

In the session-based recommendation algorithm, a better class of methods is to model the complex interaction relationship within the session as a graph structure, and then use the graph neural network to capture the deep features of the item from it. However, most models do not deeply mine the effective information contained in the sequence temporal relationship, nor do they pay attention to the auxiliary contribution of the global distance in different sessions to the item representation. This paper proposes a session-based recommendation model that integrates the temporal sequence of session interactions and the global distance-awareness of items with graph neural networks (TSDA-GNN). First, according to all session sequences, a global graph, a session graph, and a feature graph are constructed. In the global graph, the average “spacing” between items is introduced to represent the association between two items in the global graph. In the session graph, the interaction timing of the item is combined as the weight information in the relationship matrix, and the connection matrix of the session graph is constructed, which can more accurately capture the association relationship between items. Finally, by fusing the feature information of the item, using a graph neural network can deeply mine user preferences hidden in the feature information of the item. The model can not only model the information transmission relationship between items in different sessions, but also further deeply mine the hidden information of global domain and item features. Multiple experiments on two benchmark datasets show that the model proposed in this paper achieves the best results in various indicators.

As a new factor of production, data element has profoundly changed our mode of production, lifestyle and social governance style. The sharing of a data element in the convergence media ecology can greatly improve the circulation of a data element and enhance the value of a data element; however, it may face problems such as insufficient sharing willingness, incomplete sharing circulation mechanism and inadequate implementation of the incentive mechanism. To solve these problems, this paper introduced the evolutionary game theory in the convergence media ecology and established the data-sharing model according to the characteristics of nodes. We analyzed the ecological node evolution path, evolutionary stable strategy and the corresponding state conditions in the model. Furthermore, we carried out the sampling experiment simulation, which verified the effectiveness of the research content in this paper. At the end of the article, we summarize and give some key factors to increase the willingness to participate in sharing in convergence media ecology. This paper enriched the research field of data element sharing in convergence media and explored the willingness and tendency of the participants. The research results can provide targeted suggestions for promoting the sharing of data elements in convergence media ecology.

In recent years, the news platform has become the primary source of information for users. However, there are few studies on the news platform, especially for the analysis and modeling of the spreading process of information. This article models the dynamic process of information spreading on the news platform. Firstly, we analyze the dynamic characteristics of user state and information value. Users of news platforms have two states, active and silent states, and users can switch between these two states. The information value determines the probability of user state conversion. We construct the mathematical model for the dynamic features of user state and information value considering these characteristics. Then, with appropriate parameter assumptions, simulation experiments are performed to analyze the regularity of information spreading. The results of the experiment show that the user’s reading speed 1/rand the conversion probabilityp(α,β,t) are important indicators that affect user state conversion. The lower reading speed and higher conversion probability can improve the transformation of the user state. Furthermore, we present some applications to promote information spreading, such as assessing the effectiveness of information spreading and controlling rumors on news platforms. Finally, we analyzed the effect of its information dissemination by taking Toutiao as an example and confirmed that the visibility and quality of information are important factors that affect information spreading. The experiments and analysis show that the dynamic mathematical model can reflect the information spreading in different situations with different parameters on the news platform.

Social bots threaten the integrity of online social platforms by spreading misinformation, manipulating public opinion, and carrying out fraudulent activities. Detecting social bots is therefore not just a classification problem: looking ahead, a detector can also act as a discriminative component in agent-based social network generation, supplying realism-assessment signals for a “Generate–Detect–Explain–Refine” loop. Existing graph-based detection methods rely mainly on social relation graphs and do not explicitly treat behavioral similarity as a separate parallel graph branch. This paper proposes a dual-branch graph neural network for Twitter bot detection in which a heterogeneous social relation graph is accompanied by a sparse, conditionally active behavior-similarity auxiliary view; the paper’s main contributions are a competitive detector and a diagnostic protocol for attributing and repairing the value of that auxiliary view. The relation branch uses a Relational Graph Convolution Network to process a heterogeneous social relation graph, while the auxiliary branch applies a Graph Attention Network to a behavior similarity graph that links users with similar follower–following ratios, tweet type distributions, and post influence metrics. Experiments on TwiBot-22 show that the proposed model reaches 89.48 ± 0.07% accuracy and 78.11 ± 0.14% macro-F1 over five random seeds at a per-seed validation-calibrated decision threshold (89.92 ± 0.07% accuracy and 77.28 ± 0.31% macro-F1 at the default 0.5 threshold). Per-class and threshold analyses further show that the default operating point is precision-oriented on the minority bot class (bot recall 54.83 ± 1.60%), while operating near the validation-calibrated threshold (τ = 0.40) raises bot recall to 64.12 ± 1.31%. Ablation studies show that the semantic text embedding provides the largest single performance contribution and that the relation branch supplies the bulk of the graph signal. A degree-stratified analysis further shows that the behavior branch is functionally active on its ≈1% covered users—2.9× more prediction changes and 4.0× larger probability shifts than on uncovered nodes—where a validation-only subgroup threshold lifts macro-F1 from 51.85 to 67.17 without retraining, so that it can be turned into a deployable calibrated component.