基于社会网络分析的网络舆论领袖发掘——以大学生就业舆情为例

结合社会网络分析方法在网络舆情研究中的现有应用,通过分析网络舆情的结构,进而发掘网络舆论领袖。通过中心度测量、核心—边缘模型位置测算和影响力系数计算对大学生就业舆情展开案例研究。社会网络分析法和内容分析法相结合所发掘的网络舆论领袖,应成为网络舆情监控中的重点。     

突发公共安全事件网络舆情治理对策研究

在互联网飞速发展的背景下,突发公共安全事件网络舆情的传播范围、影响力、破坏力、渗透力等得到空前强化.新时代有关突发公共安全事件网络舆情的治理对策研究愈发重要.本文从传播脉络、主题、用户属性三个层次、九个方面,提出了相应的舆情干预、引导与治理对策.研究发现,厘清传播脉络、表明自身态度、重视意见领袖、提升网民素质、增强资源...     

我国少数民族语言网络舆情语言特点分析

网络舆情是指在特定的社会空间和时间内,以社会群体或者个人的形式利用互联网这一媒介相互进行信息沟通和信息传播的过程中,反映出来的针对公共事物所表达的情绪及持有的态度和行为倾向的集合。在网络信息资源管理中,我国少数民族语言网络舆情分析是非常重要的一项内容,已经越来越受到各领域的广泛关注。本文首先介绍了我国少数民族语言网络舆情分析的概况及其特征,并针对我国少数民族语言网络舆情语言分析技术未来的发展进行了探讨分析。     

网络舆情监测系统的研究与实现

网络舆情作为一种重要的舆情形式,具有形成速度快,受众人群广等特点,对国家和社会的影响越来越重大。互联网用户可以自由地在微博、论坛、博客等中发表有关社会中各类现实问题的态度和意见。监测网络舆情的主要手段就是利用网络爬虫对目标网络的页面数据进行挖掘,然后对挖掘的数据进行分类处理,并科学地统计舆情信息。本文主要分析网络舆情的特征和处理对策,并利用网络爬虫、全文检索、关键词评分、以及科学数理统计等手段对网络舆情监测系统的原理进行探索与系统实现。     

科技期刊编辑要注意审稿过程中的惯性思维意识和自以为是心态

就科技期刊编辑审稿意见加以分析研究,提出惯性思维意识和自以为是心态,并就如何避免出现不当审稿意见给出了具体预防措施。     

网络舆情研究中的仿真方法应用综述*

引入仿真方法进行网络舆情演化、引导机理的探索是近年来网络舆情研究的一个热点。在对我国网络舆情研究中仿真方法的应用状况进行文献梳理和评述的基础上,详细介绍了仿真方法的对象、建模理论与方法和相关仿真平台,探讨了当前的研究不足与未来的研究方向。     

Applying the communication theory of Diffusion of Innovations to economic sciences: a response to the ‘Using gossips to spread information’ experiments conducted by the 2019 Nobel Laureates

ABSTRACT

Drs Abhijit Banergee, Esther Duflo, and Michael Kremer won the 2019 Nobel Prize in Economic Sciences for their remarkable series of large-scale field experiments to lessen global poverty. The main theoretical framework that they employed was the diffusion of innovations research and practice paradigm (DOI) which has had a long presence in communication research dating back to the 1940s. Here, we reviewed the Nobel laureates’ article, ‘Using gossips to spread information: Theory and evidence from two randomized controlled trials,’ that is illustrative of how economists applied the communication theory of diffusion of innovations to their projects of social change. The present article poses questions and makes recommendations for similar future projects from a communication perspective.     

微博舆情关键节点情感倾向分析及思想引领研究

[目的/意义]为防止微博失实舆情爆发给社会带来的严重后果，研究如何对微博中关键节点的倾向性进行分类，以及时制止恶意煽动群众情绪的节点，防止更多微博用户被误导，并通过不同的思想引领方式，由点及面地对微博用户进行思想引领，更好地净化微博舆情环境。[方法/过程]利用超网络和动态网络分析方法确定关键节点，通过对其情感倾向性进行分析，提供不同的引领策略。[结果/结论]微博舆情生命周期内会出现5类关键节点，思想引领可分为智能引领和智慧引领。     

An unsupervised aspect extraction strategy for monitoring real-time reviews stream

One of the most important opinion mining research directions falls in the extraction of polarities referring to specific entities (aspects) contained in the analyzed texts. The detection of such aspects may be very critical especially when documents come from unknown domains. Indeed, while in some contexts it is possible to train domain-specific models for improving the effectiveness of aspects extraction algorithms, in others the most suitable solution is to apply unsupervised techniques by making such algorithms domain-independent and more efficient in a real-time environment. Moreover, an emerging need is to exploit the results of aspect-based analysis for triggering actions based on these data. This led to the necessity of providing solutions supporting both an effective analysis of user-generated content and an efficient and intuitive way of visualizing collected data. In this work, we implemented an opinion monitoring service implementing (i) a set of unsupervised strategies for aspect-based opinion mining together with (ii) a monitoring tool supporting users in visualizing analyzed data. The aspect extraction strategies are based on the use of an open information extraction strategy. The effectiveness of the platform has been tested on benchmarks provided by the SemEval campaign and have been compared with the results obtained by domain-adapted techniques.     

How did Americans Really Think About the Apple/FBI Dispute? A Mixed-method Study

ABSTRACT

Second-level agenda-setting suggests that news media influence how we think. As a case study examining the nature and effects of mainstream news media’s coverage of the 2015 Apple/FBI dispute about data privacy versus national security, this study found via content analysis that a majority of articles covering the dispute (73.7%) made the same potentially misleading claim about how the American public feels about the dispute. Nearly half (45.6%) of those articles made public opinion claims without offering empirical evidence, and almost all articles (97.4%) that cited the Pew survey appeared to have inadvertently created an unsubstantiated social reality. Then, this study found in a subsequent experiment that, consistent with impersonal influence, the above-mentioned news portrayals significantly affected the participants’ view on Americans’ collective opinion towards the Apple/FBI dispute. The long-term effect of this journalistic oversight is notable. Theoretical implications and practical recommendations for future science communication in the news are discussed.