A multimodal time-series method for gifting prediction in live streaming platforms     

《Information processing & management》2023,60(3):103254

Viewer gifting is an important business mode in live streaming industry, which closely relates to the income of the platforms and streamers. Previous studies on gifting prediction are often limited to cross-section data and consider the problem from the macro perspective of the whole live streaming. However, the multimodal information and the time accumulation effect of live streaming content on viewer gifting behavior are ignored. In this paper, we put forward a multimodal time-series method (MTM) for predicting real-time gifting. The core module of the method is the multimodal time-series analysis (MTA), which targets at effectively fusing multimodal information. Specifically, the proposed orthogonal projection (OP) model can promote cross-modal information interaction without introducing additional parameters. To achieve the interaction of multi-modal information at the same level, we also design a stackable joint representation layer, which makes each target modality's representation (visual, acoustic and textual modality) can benefit from all the other modalities. The residual connections are introduced as well to ensure the integration of low-level and high-level information. On our dataset, our model shows improved performance compared to other advanced models by at least 8% on F1. Meanwhile, the MTA is able to meet the real-time requirements of the live streaming setting, and has demonstrated its robustness and transferability in other tasks. Our research may offer some insights about how to efficiently fuse multimodal information, and contribute to the research on viewer gifting behavior prediction in the live streaming context.  相似文献   

Back to common sense: Oxford dictionary descriptive knowledge augmentation for aspect-based sentiment analysis     

《Information processing & management》2023,60(3):103260

  相似文献   

电子书用户使用意愿影响模型构建与实证     

杨方铭  张志强 《图书情报工作》2020,64(9):85-94

[目的/意义] 探究用户使用电子书意愿的影响因素，以有助于电子书产业走出缓慢的发展困境。[方法/过程] 以UTAUT2、使用满足理论为基础，从需求满足和外部情景因素两个层面构建影响因素模型，并将需求满足细化为内容需求、社交互动需求和休闲娱乐需求3个测量变量。采用问卷调查方法收集有效样本1 013份，使用AMOS21软件对模型进行验证。[结果/结论] 研究发现，需求满足、阅读习惯、价格价值、社会影响对使用意愿有正向影响作用，而激励措施对使用意愿有负向影响作用，努力期望对使用意愿的影响不显著，并依据研究结果提出促进电子书产业发展的建议。  相似文献   

Responsible and human centric AI-based insurance advisors     

《Information processing & management》2023,60(3):103273

The domain about what it means to give responsible and human centric recommendations in the context of Artificial Intelligence (AI)-based insurance has not yet been fully explored. In this article, we therefore, first provide an in-depth analysis and perform a systematic literature review on (i) the specifications and requirements for such systems from a regulation point of view, (ii) instructions on which data they can rely upon, (iii) which recommender techniques can be used for developing such an advisor, (iv) off-the-shelf components for the trustworthy, responsible, and ethical behavior of this AI-empowered tool. Then, we present a novel approach, based on AI, to suggest insurance coverage for users and families, as well as instructions on how to design such a system. The solution, as proposed in our paper, will be transparent, trustworthy, and responsible to the final users and thus, hopefully, better accepted by customers. After describing a possible system design and architecture, we critically discuss the challenges and opportunities for the deployment of such systems in insurance companies.  相似文献   

Online portfolio management via deep reinforcement learning with high-frequency data     

《Information processing & management》2023,60(3):103247

Recently, models that based on Transformer (Vaswani et al., 2017) have yielded superior results in many sequence modeling tasks. The ability of Transformer to capture long-range dependencies and interactions makes it possible to apply it in the field of portfolio management (PM). However, the built-in quadratic complexity of the Transformer prevents its direct application to the PM task. To solve this problem, in this paper, we propose a deep reinforcement learning-based PM framework called LSRE-CAAN, with two important components: a long sequence representations extractor and a cross-asset attention network. Direct Policy Gradient is used to solve the sequential decision problem in the PM process. We conduct numerical experiments in three aspects using four different cryptocurrency datasets, and the empirical results show that our framework is more effective than both traditional and state-of-the-art (SOTA) online portfolio strategies, achieving a 6x return on the best dataset. In terms of risk metrics, our framework has an average volatility risk of 0.46 and an average maximum drawdown risk of 0.27 across the four datasets, both of which are lower than the vast majority of SOTA strategies. In addition, while the vast majority of SOTA strategies maintain a poor turnover rate of approximately greater than 50% on average, our framework enjoys a relatively low turnover rate on all datasets, efficiency analysis illustrates that our framework no longer has the quadratic dependency limitation.  相似文献   

基于系统动态学方法的弱信号生命周期建模与仿真     

董尹  刘千里  宋继伟 《图书情报工作》2019,63(13):75-84

[目的/意义]为增强弱信号的内涵研究，对其全生命周期过程下的各阶段要素以及要素间的联系进行探寻，以期获得一定程度上的理论贡献，同时也为相关组织在开展弱信号管理实践时提供理论指导。[方法/过程]在对弱信号概念研究现状进行梳理的基础上，结合意义构建理论给出了弱信号概念界定。随后，通过与信息生命周期、新兴议题生命周期进行类比，提出弱信号生命周期理念。进而采用系统动态学方法开展系统思考，使用因果回路图进行系统建模，运用存量流量图进行仿真模拟。[结果/结论]弱信号生命周期包含4个阶段：侦测、关联、传递、抉择，相应的系统动态学模型所具备的现实性得到验证，且通过情景模拟确认了4个关键辅助变量：外界噪声干扰程度、弱信号分析效率、组织内相互信任程度、决策者信任程度。在整体研究的基础上，给出弱信号管理过程中可能会遇到的障碍以及应对策略。  相似文献   

Quantifying revolutionary discoveries: Evidence from Nobel prize-winning papers     

《Information processing & management》2023,60(3):103252

Numerous metrics have been developed to identify revolutionary science which is crucial for advancing science. However, these metrics have rarely successfully identified revolutionary discoveries. We propose a two-dimension metric to quantify revolutionary discoveries by combining the consolidation-or-destabilization (CD) index with the citation count. To verify the validity of the metric, we utilize multivariate linear regression to investigate the differences in the CD indices and citations between 164 Nobel prize-winning papers from 1976 to 2016 (i.e., revolutionary science) and 9,034 counterparts that are similar to the Nobel prize-winning papers in terms of bibliographic information. We find that our proposed metric successfully shows a significant and distinct difference between the Nobel prize-winning papers and their counterparts in that the former receive around 880 more citations and 0.07 higher CD indices than the latter. The reliability of our proposed measure is robust.  相似文献   

数据驱动视野下高校智慧图书馆建设及服务规划——兼论“十四五”时期智慧图书馆发展路径     

邵波  许苗苗  王怡 《图书情报工作》2021,65(1):41-46

[目的/意义] 在科研全面数据化和“十四五”规划的背景下，高校图书馆建设方向和路径对教学和科研具有重大影响，本文旨在提出图书馆智慧化转型的下一步落地和实践思路。[方法/过程] 梳理高校图书馆发展现状，解析发展新态势，以数据意识为出发点，尝试构建智慧图书馆在技术、服务、空间等方面的发展方案。[结果/结论] 智慧图书馆的建设应重点在智能设备、智慧服务平台和智慧空间上“下深功”，此外还需在馆员角色和联盟建设上深入思考。  相似文献   

Exploring askers’ switching from free to paid social Q&A services: A perspective on the push-pull-mooring framework     

Zhouying Liu  Yuxiang Zhao  Si Chen  Shijie Song  Preben Hansen  Qinghua Zhu 《Information processing & management》2021,58(1):102396

The purpose of this study is to explore the factors that prompt askers to switch from free to paid social question-and-answer (SQA) services. Prior studies have investigated users’ motivations and participation in free and paid SQA services; however, little attention has been paid to askers’ switching behavior. We empirically analyzed the content of qualitative interviews from 64 askers on a well-known SQA platform in China. Based on the push-pull-mooring framework, we identified and classified factors that influenced askers’ to switch from free to paid Q&A services, using the critical incident technique, after which we calculated the entropy weights of the 16 subcategories before and after the switch, using the entropy weight method. The findings suggest that askers’ switching behavior was influenced by push factors (i.e., dissatisfaction with the free SQA service), pull factors (i.e., satisfaction with the paid SQA service), and mooring factors (i.e., social factors, personal factors, situational factors). Moreover, the findings show that the effects of these factors vary significantly before and after a switch. Dissatisfaction with the quality of information from the free SQA service would influence users before a switch, whereas satisfaction with the quality of information from the paid SQA service would influence them after a switch. In terms of mooring factors, the effects of social and personal factors on askers’ switching behavior, especially subjective norms and cognitive lock-in, turn out to be less significant after a switch, whereas the effect of trust is more significant. Besides, the effects of situational factors are more or less the same before and after a switch. To the best of our knowledge, this paper is one of the first attempts to explore factors that affect askers’ switching behavior and to shed light on the managerial strategies of paid SQA services.  相似文献   

在线健康社区用户个人健康信息管理行为特征研究   总被引：3，自引：1，他引：2  

杨梦晴  朱庆华 《图书情报工作》2020,64(1):105-112

[目的/意义] 旨在对在线健康社区用户的个人健康信息管理行为特征进行分析，并在此基础上，对"平台-PHIM-健康目标"这一模式中的元素之间的关系进行探讨。[方法/过程] 选择患有红斑狼疮的在线健康社区用户作为调查对象。采用聚类方法对个人健康信息管理行为的总体测度水平不同的群体进行识别；利用单因素方差分析（One-way ANOVA）对不同群组进行比较研究。[结果/结论] 将依托在线健康社区进行的个人健康信息管理行为界定为健康信息发现、健康信息互动和健康信息分享。从数据分析结果来看，首先，在线健康社区的红斑狼疮患者在个人健康信息管理行为水平上存在显著的高低差异。第二，用户所感知到的社会支持与其个人健康信息管理水平存在正相关关系。第三，个人健康信息管理与用户健康目标之间存在正相关关系。本研究为在线健康社区完善其服务方式，促进慢性病人个人健康信息管理水平提高提供合理建议。  相似文献