LGCCT: A Light Gated and Crossed Complementation Transformer for Multimodal Speech Emotion Recognition.

Semantic-rich speech emotion recognition has a high degree of popularity in a range of areas. Speech emotion recognition aims to recognize human emotional states from utterances containing both acoustic and linguistic information. Since both textual and audio patterns play essential roles in speech emotion recognition (SER) tasks, various works have proposed novel modality fusing methods to exploit text and audio signals effectively. However, most of the high performance of existing models is dependent on a great number of learnable parameters, and they can only work well on data with fixed length. Therefore, minimizing computational overhead and improving generalization to unseen data with various lengths while maintaining a certain level of recognition accuracy is an urgent application problem. In this paper, we propose LGCCT, a light gated and crossed complementation transformer for multimodal speech emotion recognition. First, our model is capable of fusing modality information efficiently. Specifically, the acoustic features are extracted by CNN-BiLSTM while the textual features are extracted by BiLSTM. The modality-fused representation is then generated by the cross-attention module. We apply the gate-control mechanism to achieve the balanced integration of the original modality representation and the modality-fused representation. Second, the degree of attention focus can be considered, as the uncertainty and the entropy of the same token should converge to the same value independent of the length. To improve the generalization of the model to various testing-sequence lengths, we adopt the length-scaled dot product to calculate the attention score, which can be interpreted from a theoretical view of entropy. The operation of the length-scaled dot product is cheap but effective. Experiments are conducted on the benchmark dataset CMU-MOSEI. Compared to the baseline models, our model achieves an 81.0% F1 score with only 0.432 M parameters, showing an improvement in the balance between performance and the number of parameters. Moreover, the ablation study signifies the effectiveness of our model and its scalability to various input-sequence lengths, wherein the relative improvement is almost 20% of the baseline without a length-scaled dot product.

Blockchain Technology, Cryptocurrency: Entropy-Based Perspective.

The large-scale application of blockchain technology is an expected to be an inevitable trend. This study revolves around published papers and articles related to blockchain technology, relevance analysis and sorting through the retrieved documents with six core layers of blockchain: Application Layer, Contract Layer, Actuator Layer, Consensus Layer, Network Layer and Data Layer. Based on the analysis results, this study found that China's research is more towards the preference and application of landing and industry and smart cities with blockchain as the underlying technology. International research is more focused on the research of finance as the underlying technology of blockchain and tries to combine crypto assets with real industries, such as crypted assets and payment systems for traditional industries. This paper studies the impact of monetary entropy on cryptocurrencies in smart cities and uses the monetary entropy formula to measure the crypto-economic entropy. We use Kolmogorov entropy to describe the degree of chaos in the cryptocurrency market in a smart city. The study illustrates the current status of blockchain technology and applications from the perspective of cryptocurrency in a smart city. We find that smart cities and cryptocurrencies have a mutually reinforcing effect.

A hybrid with distributed pooling blockchain protocol for image storage.

As a distributed storage scheme, the blockchain network lacks storage space has been a long-term concern in this field. At present, there are relatively few research on algorithms and protocols to reduce the storage requirement of blockchain, and the existing research has limitations such as sacrificing fault tolerance performance and raising time cost, which need to be further improved. Facing the above problems, this paper proposes a protocol based on Distributed Image Storage Protocol (DISP), which can effectively improve blockchain storage space and reduces computational costs in the help of InterPlanetary File System (IPFS). In order to prove the feasibility of the protocol, we make full use of IPFS and distributed database to design a simulation experiment for blockchain. Through distributed pooling (DP) algorithm in this protocol, we can divide image evidence into recognizable several small files and stored in several nodes. And these files can be restored to lossless original documents again by inverse distributed pooling (IDP) algorithm after authorization. These advantages in performance create conditions for large scale industrial and commercial applications.

Online Public Rumor Engagement Model and Intervention Strategy in Major Public Health Emergencies: From the Perspective of Social Psychological Stress.

During major public health emergencies, a series of coupling problems of rumors getting out of control and public psychological imbalance always emerge in social media, which bring great interference for crisis disposal. From the perspective of social psychological stress, it is important to depict the interactive infection law among distinct types of rumor engagers (i.e., advocates, supporters, and amplifiers) under different social psychological stress states, and explore the effectiveness of rumor intervention strategies (i.e., hindering and persuasion) from multiple dimensions, to scientifically predict the situation of public opinion field and guide the public to restore psychological stability. Therefore, this paper constructs an interactive infection model of multiple rumor engagers under different intervention situations based on a unique user-aggregated dataset collected from a Chinese leading online microblogging platform ("Sina Weibo") during the COVID-19 in 2020. The simulation result shows that (1) in the period of social psychological alarm reaction, the strong level of hindering intervention on the rumor engagers leads to more serious negative consequences; (2) in the period of social psychological resistance, the persuasion and hindering strategies can both produce good outcomes, which can effectively reduce the overall scale of rumor supporters and amplifiers and shorten their survival time in social media; (3) in the period of social psychological exhaustion, rumor intervention strategies are not able to have a significant impact; (4) the greater the intensity of intervention, the more obvious the outcome. Experimental findings provide a solid research basis for enhancing social psychological stress outcomes and offer decision-making references to formulate the rumor combating scheme.

The Continued Use of Social Commerce Platforms and Psychological Anxiety-The Roles of Influencers, Informational Incentives and FoMO.

Why does the continued use of social commerce platforms fail to promote consumer wellbeing? This study explores the roles of influencers, informational incentives and fear of missing out (FoMO) in the relationships between social commerce platform use and consumer mental health. Data were obtained through questionnaires, as well as constructing a research model. Statistical analysis and path analysis of the structural equation model were performed by the software IBM SPSS and AMOS, and the following results were obtained. (1) Influencer expertise and interactivity, informational incentives and FoMO have a significant impact on consumers' continued use of social commerce platforms. (2) Materialism has no significant effect on consumer social commerce platform use. (3) FoMO mediates the relationships between informational incentives and continued use of social commerce platforms. (4) Consumers' continuous use of social commerce platforms has a strong relationship with mental health. (5) Continued use of social commerce platforms can lead to intense social engagement, as well as more severe outcomes such as psychological anxiety and compulsive buying. The findings of the paper have important implications for the development of social business theory and management practice.

Perceiving Social-Emotional Volatility and Triggered Causes of COVID-19.

Health support has been sought by the public from online social media after the outbreak of novel coronavirus disease 2019 (COVID-19). In addition to the physical symptoms caused by the virus, there are adverse impacts on psychological responses. Therefore, precisely capturing the public emotions becomes crucial to providing adequate support. By constructing a domain-specific COVID-19 public health emergency discrete emotion lexicon, we utilized one million COVID-19 theme texts from the Chinese online social platform Weibo to analyze social-emotional volatility. Based on computed emotional valence, we proposed a public emotional perception model that achieves: (1) targeting of public emotion abrupt time points using an LSTM-based attention encoder-decoder (LAED) mechanism for emotional time-series, and (2) backtracking of specific triggered causes of abnormal volatility in a cognitive emotional arousal path. Experimental results prove that our model provides a solid research basis for enhancing social-emotional security outcomes.