The continuous combination of digital network technology and traditional financial services has given birth to digital financial networks, which explore massive economic data under the AI-driven models to achieve intelligent connections among financial institutions, markets, transactions, and instruments. Empirical asset pricing is a challenging task in financial analysis, which has attracted research attention. However, existing studies only focus on tackling the challenges of equity risk premium in the single stock market. Considering multiple economic linkages between the two countries, the transaction history of the US stock market as empirical knowledge is a powerful supplement to improve the prediction of equity risk premium in the China market. In this paper, we aim to fully leverage the prior information in two stock markets for empirical asset pricing models. Due to the rich financial domain knowledge, there may be various characteristic signals that partially overlap in different periods. To address these issues, we propose a framework based on long-short dual-mode knowledge distillation, termed as LSDM-KD, which incorporates US and China stock market models, and a shared characteristic signals model. The method effectively understands the relationships between assets and market behaviour, reducing reliance on expensive correlation databases and professional knowledge. Extensive experiments conducted on US and China stock market datasets demonstrate that our LSDM-KD can significantly improve the performance of empirical asset pricing.

News recommendation (NR) is critical for helping users to navigate the vast amount of information on online news platforms. However, the key challenges of tackling the cold-start problem, comprehensively modeling user interests and accurately encoding news semantics in NR have not yet been effectively addressed by existing methods. In this paper, we propose to alleviate the cold-start problem by exploiting news popularity. We also argue that the browsing history of a user can be organized as a personalized hypergraph to augment user interest modeling. Furthermore, we suggest enriching the representation of a candidate news article by retrieving its similar news. Our proposed NR method, named P opularity P rediction with S emantic R etrieval (PPSR), features a retrieval-driven popularity predictor that leverages click records to predict news popularity by incorporating semantic retrieval. It also comprises a hypergraph-based user encoder that mines the rich and diverse relatedness among news in a user’s browsing history. In addition, it designs a semantic-enhanced news encoder that retrieves and utilizes similar news in the training set to enrich semantic encoding for candidate news. Experiments on real-world datasets show that our PPSR can outperform the state-of-the-art methods in terms of higher recommendation accuracy and can well mitigate both the user-level and news-level cold-start problems.

Ideology detection (ID) is important for gaining insights about peoples' opinions and stances on our world and society, which can find many applications in politics, economics and social sciences.It is not uncommon that a piece of text can contain descriptions of various issues.It is also widely accepted that a person can take different ideological stances in different facets.However, existing datasets for the ID task only label a text as ideologically left-or right-leaning as a whole, regardless whether the text containing one or more different issues.Moreover, most prior work annotates texts from data resources with known ideological bias through distant supervision approaches, which may result in many false labels.With some theoretical help from social sciences, this work first designs an ideological schema containing five domains and twelve facets for a new multifaceted ideology detection (MID) task to provide a more complete and delicate description of ideology.We construct a MITweet dataset for the MID task, which contains 12,594 English Twitter posts, each annotated with a Relevance and an Ideology label for all twelve facets.We also design and test a few of strong baselines for the MID task under in-topic and cross-topic settings, which can serve as benchmarks for further research.

Persuasion, which is the act of convincing someone to change their idea, attitude, or opinion, happens anywhere and anytime in social life. In this paper, based on the social judgment theory, we propose a novel asynchronous evolution Deffuant-Weisbuch opinion dynamics model by introducing the latitude of non-commitment. In our model, when agents communicate with each other, the evolution of their opinions depend not only on the opinion of themselves and their neighbors but also on the latitude where they locate, thus an opinion evolution rule that close to reality is designed. The model can well explain the persuasion process and captures the assimilation phenomenon in social networks. Simulation results show that the model can finally reach a stable state. Moreover, network topology, initial distribution of agents’ opinions and the range of latitudes of non-commitment all have an impact on the convergence time of opinions.

The classic Hegselmann–Krause opinion dynamics model plays an important role in analyzing opinion evolution among people. However, it is not in line with the reality of interpersonal communication during the modern online social times, in which people are easy to exchange opinions with another one who agrees or disagrees with themselves on certain issues by social networks. In this paper, considering the effects of the one-sided versus two-sided presentation of a controversial issue, we improve the classic HK model and propose a novel information-type education-based Hegselmann–Krause model. In our work, we formulate rules of how agents’ opinions change and carry out simulation experiments on networks with different proportions of high-educated agents. Extensive experiments on artificially generated networks show that it is more difficult for someone to reach a consensus with another one who is within a group with a higher proportion of low-educated people than with a higher proportion of high-educated people, which verify the effectiveness of the proposed model.

The COVID-19 outbreak a pandemic, which poses a serious threat to global public health and lead to a tsunami of online social media. Individuals frequently express their views, opinions and emotions about the events of the pandemic on Twitter, Facebook, etc. Many researches try to analyze the sentiment of the COVID-19-related content from these social networks. However, they have rarely focused on the vaccine. In this paper, we study the COVID-19 vaccine topic from Twitter. Specifically, all the tweets related to COVID-19 vaccine from December 15th, 2020 to February 10th, 2021 are collected by using the Twitter API, then the unsupervised learning VADER model is used to judge the emotion categories (positive, neutral, negative) and calculate the sentiment value of the dataset. Based on the interaction between users, a communication topological network is constructed and the emotional direction is explored. We find that people had different sentiments between Chinese vaccine and those in other countries. The sentiment value might be affected by the number of daily news cases and deaths, the nature of key issues in the communication network. And revealing that the key nodes in the social network can produce emotional contagion to other nodes.

The existing opinion dynamics models based on the impact of opinion leaders tend to only consider the impact of opinion leaders on normal individuals, but ignore the impact of normal individuals on opinion leaders. Normal individuals in social networks can also change the opinions of opinion leaders by initiative affection mobilization. In this paper, an affection mobilization leadership index (AMLI) is used to identify opinion leaders and influential agents who can mobilize affection initiatively. A novel opinion dynamics affection mobilization-based Hegselmann-Krause model (AMHK) is then proposed. Extensive experiments on both artificially generated and real-trace network datasets verify the effectiveness and efficiency of the proposed model. Appropriate proportion of influential agents can promote the reach of consensus, while excess influential agents could lead a consensus with fragmented opinions, which provides a significant train of thought in guiding public opinion.

Hegselmann-Krause model plays an important role in opinion dynamics. Many researchers try to improve the classic Hegselmann-Krause model from different aspects. However, the influence of agents' media literacy on the opinion evolution always have not been taken into consideration. Due to the differences in accessing, analyzing, and producing information between agents, the media literacy gap will evidently affect their communication in real life. In this paper, media literacy is introduced to improve the traditional HK model, and a novel opinion dynamics Hegselmann-Krause model with Media Literacy (HKML) is proposed. In our work we not only consider the confidence bound, but also consider the media literacy of agents. Agents under the HKML model can select and communicate with influential neighbors through a more accuracy criterion. Numerical simulation results demonstrate that the HKML model breaks through the limit of the confidence bound, which makes more communication with less convergence time. Moreover, the HKML model shows strong robustness with the environmental noise.

As people spend considerable time on digital media, online platforms have functioned as major channels for public expression. Understanding the formation and diffusion of sentiment or emotion is benefit to create a healthy environment for public discussion. In this paper, based on emotion contagion and opinion dynamics, we established a specially designed model for dynamic emotion diffusion. The method of computational modelling and simulation is applied to simulate the real-world social interactions. Factors including the distribution of initial emotion, credibility threshold, self-assertiveness and emotion decay function that might influence sentiment diffusion are analyzed, a novel concept of emotion fluctuation is introduced to predict agents' behavior. Simulation results demonstrate that all these factors mentioned above can influence the evolution of emotion, leading to its fragmentation, polarization or consensus.

Social emotion classification is to estimate the distribution of readers' emotion evoked by an article. In this paper, we design a new neural network model by encoding sentence syntactic dependency and document topical information into the document representation. We first use a dependency embedded recursive neural network to learn syntactic features for each sentence, and then use a gated recurrent unit to transform the sentences' vectors into a document vector. We also use a multi-layer perceptron to encode the topical information of a document into a topic vector. Finally, a gate layer is used to compose the document representation from the gated summation of the document vector and the topic vector. Experiment results on two public datasets indicate that our proposed model outperforms the state-of-the-art methods in terms of better average Pearson correlation coefficient and MicroF1 performance.

Event recommendation has become an important issue in event-based social networks (EBSN). In this paper, we study how to exploit diverse relations in an EBSN as well as individual history preferences to recommend preferred events. We first construct a hybrid graph consisting of different types of nodes to represent available entities in an EBSN. The graph uses explicit relations as edges to connect nodes of different types; while transferring implicit relations of event attributes to interconnect the event nodes. After executing the graph random walking, we obtain the candidate events with high convergency probabilities. We next extract a user preference from his attended events to further compute his interest similarities to his candidate events. The recommended event list is then obtained by combining the two similarity scores. Data sets from a real EBSN are used to examine the proposed scheme, and experiment results validate its superiority over peer schemes.