报告主题:社交网络上议题社群的公共焦虑研究

报告摘要:Although a number of researches on individual level anxiety evalua- tion have been proposed, there are few researches on evaluating the public anxiety of a social network community, which can benefit various social network analysis tasks. However, we can not simply average anxiety scales of all individuals to calculate the public anxiety score of a community, because: (1) individuals are influenced by their connections in a community, so impacts from interpersonal relations on individuals’ anxiety scales should be considered, i.e., the Structural factor; (2) public anxiety always relates to certain topics, topical discussions also reflect a community’s anxiety level, which should also be considered, i.e., the Topical factor. In this paper we initiate the study of evaluating the public anxiety of topic-based social network communities (TSNC). We propose an evaluation framework to project a TSNC’s anxiety level into a score in the [0, 1] range, using both Structural and Topical factors. We devise a cascading model to dynamically compute the anxiety score using the Structural influence. We propose a stochastic model to measure anxiety score of social network messages using a generalized user, and design a tree structure (MC-Tree) to organize messages of a TSNC to effectively compute anxiety score from the Topical factor. For large communities, computing public anxiety in real-time can be expensive, we show how to use a small sample of the community to compute the public anxiety within given confidence interval. Our model exhibits more than 80% precision and 90% recall in an empirical study on real-world data sets from Weibo.

嘉宾简介:塔娜,中国人民大学新闻学院讲师,中国人民大学新闻与社会发展研究中心研究员。2017年毕业于清华大学计算机系,获计算机科学与技术专业博士学位。研究方向为计算传播学。近年来以第一作者或通讯作者身份发表多篇CCF(中国计算机学会)A类及SCI索引论文。目前主持一项国家自然科学基金项目青年项目,及一项北京市社会科学基金项目青年项目。

成为VIP会员查看完整内容
0
10

相关内容

社会网络(英语:Social network),是由许多节点构成的一种社会结构,节点通常是指个人或组织,社会网络代表各种社会关系,经由这些社会关系,把从偶然相识的泛泛之交到紧密结合的家庭关系的各种人们或组织串连起来。社会网络由一个或多个特定类型的相互依存,如价值观、理想、观念、金融交流、友谊、血缘关系、不喜欢、冲突或贸易。由此产生的图形结构往往是非常复杂的。

We present Meena, a multi-turn open-domain chatbot trained end-to-end on data mined and filtered from public domain social media conversations. This 2.6B parameter neural network is trained to minimize perplexity, an automatic metric that we compare against human judgement of multi-turn conversation quality. To capture this judgement, we propose a human evaluation metric called Sensibleness and Specificity Average (SSA), which captures key elements of good conversation. Interestingly, our experiments show strong correlation between perplexity and SSA. The fact that the best perplexity end-to-end trained Meena scores high on SSA (72% on multi-turn evaluation) suggests that a human-level SSA of 86% is potentially within reach if we can better optimize perplexity. Additionally, the full version of Meena (with a filtering mechanism and tuned decoding) scores 79% SSA, 23% higher than the next highest scoring chatbot that we evaluated.

0
10
下载
预览

报告主题:网络表示学习

报告摘要:数据特征的有效表示是机器学习任务中最为关键环节之一。网络数据(如社交网络、信息网络等)作为普适而广泛的数据呈现形式,对它的高效表示学习是近年来数据挖掘和机器学习领域的研究热点之一。本报告将重点围绕如下内容展开:(1)网络表示学习的基本概念;(2)几类新型网络表示学习方法,包括:网络Tag表示、域自适应表示、基于网络划分的表示以及内存自适应的表示方法等。

嘉宾简介:宋国杰,北京大学信息科学技术学院副教授。研究方向包括:网络大数据分析、机器学习&数据挖掘、社会网络分析和智能交通系统。主持了包括国家高技术研究发展计划(863计划)、国家科技支撑计划、国家自然科学基金等纵向课题10多项;主持了国际(内)科研机构合作课题、企业横向合作课题等20余项。国家级精品课程主讲教师,两度获得北京大学教学成果一等奖(2012、2009)。在包括国际顶级期刊TKDE、TPDS、TITS以及国际顶级会议KDD、IJCAI、AAAI等发表论文100余篇,是多个国际顶级会议(KDD、WWW、AAAI、IJCAI等)的程序委员。申请国家发明专利10项,软件著作权3项。研究成果获“2012年度中国公路学会科学技术奖一等奖”、“2012年度山西省科学技术奖二等奖”和“2013年度中国公路学会科学技术奖一等奖”。

成为VIP会员查看完整内容
0
27

报告主题:互联网、社会互动和群体行为

报告摘要:人与人的互动是人类社会赖以形成、维持和生长的微观基础。互联网的出现,深刻地改变了社会互动的广度、深度和模式。其中一个重要的效应,是整个社会日趋散众化。散众的基本特征是,基于互联网时代信息的过载、自闭和高频流动,社会各成员之间难以形成深入的情感交流和价值共识,但是基于无远弗届的互联网而形成的物理联系,却又特别容易同频共振,不时引发规模巨大而又能量惊人的群体行为。这样一种啸散啸聚的群体行为,对于社会秩序的维持和发展是一个严重挑战,从而是当前全球和中国社会治理中必须应对的难题,亟需社会各界共同思考。

嘉宾简介:冯仕政,中国人民大学社会与人口学院教授、院长。主要从事政治社会学、组织社会学、社会治理与国家构建、社会转型与政治秩序等领域的研究。在国内外重要学术期刊上发表论文数十篇,著有《当代中国的社会治理与政治秩序》、《西方社会运动理论研究》、《社会治理新蓝图》等书。曾主持国家社科基金重点课题、“马克思主义理论研究和建设工程”重大课题;获北京市哲学社会科学优秀成果一等奖、霍英东教育基金高等院校青年教师奖、宝钢优秀教师奖、北京市高等教育优秀教学成果奖、高等教育国家级教学成果奖。入选教育部“新世纪优人才”、“青年长江学者”,北京市新世纪社科理论人才“百人工程”和“四个一批”理论人才培养工程。

成为VIP会员查看完整内容
互联网、社会互动和群体行为.pptx.pdf
0
12

报告主题:Aspect-Oriented Syntax Network for Aspect-Based Sentiment Analysis

报告摘要:Aspect-based sentiment analysis aims to determine the sentimental polarity towards a specific aspect in reviews or comments. Recent attempts mostly adopt attention-based mechanisms to link opinion words to their respective aspects in an implicit way. However, due to the tangle of multiple aspects or opinion words occurred in one sentence, the models often mix up the linkages. In this paper, we propose to encode sentence syntax explicitly to improve the effect of the linkages. We define an aspect-oriented dependency tree structure, which is reshaped and pruned from an ordinary parse tree, to express useful syntax information. The new tree is then encoded into a multifaceted syntax network, to be used in combination with attention-based models for prediction. Experimental results on three datasets from SemEval 2014 and Twitter show that, with our syntax network, the aspect-sentiment linkages can be better established and the attention-based models are substantially improved as a result.

嘉宾简介:权小军,教授,博士生导师。先后于中国科学技术大学计算机系、香港城市大学计算机系、美国罗格斯大学商学院、美国普渡大学计算机系、香港城市大学语言学与翻译系、新加坡科技研究局资讯通信研究院从事自然语言处理、文本挖掘和机器学习的研究工作,在国际知名期刊和会议如IEEE T-PAMI,ACM TOIS,ACL,IJCAI,SIGIR等发表论文30余篇。权小军2012年毕业于香港城市大学,获博士学位,回国前就职于新加坡科技研究局资讯通信研究院,任研究科学家,期间除从事相关方向的基础研究外,也同工业界紧密合作探索研究成果的应用。

成为VIP会员查看完整内容
Aspect-Oriented Syntax Network for Aspect-Based Sentiment Analysis -权小军.pdf
0
14

论坛嘉宾:魏忠钰 复旦大学 副教授

报告主题:图卷积神经网络在计算金融等交叉学科领域的应用研究

报告摘要:基于图的模型能够描绘特定场景中的实体信息以及实体之间的关系,一直以来被各个学科的学者采用,在相关领域进行不同任务的建模和计算。近年来,图卷积神经网络在大规模图数据上的机器学习任务中有很好的性能表现,这也在交叉学科领域的学者中引起广泛的关注。本次报告将梳理图卷积神经网络在一些交叉学科进行表示学习以及标签预测的工作,并重点介绍报告人近期在计算金融等领域使用图卷积神经网络开展的应用研究工作。

嘉宾简介:魏忠钰,复旦大学大数据学院副教授,香港中文大学博士,美国德州大学达拉斯分校博士后,中文信息学会社交媒体处理专委会通讯委员,中国中文信息学会青年工作委员会委员。主要研究领域为自然语言处理,机器学习和社会媒体处理,专注于自动化文本生成(Text Generation)和论辩挖掘(Argumentation Mining)的研究,在相关领域在国际会议、期刊如CL,ACL,SIGIR,EMNLP,AAAI,IJCAI, Bioinformatics等发表学术论文40余篇。担任多个重要的国际会议或者期刊评审,入选2017年度上海市青年科技英才扬帆计划。

成为VIP会员查看完整内容
SMP 2019 - 表示学习论坛 - 魏忠钰 - 复旦大学.pptx.pdf
0
28

机器学习可解释性,Interpretability and Explainability in Machine Learning

  • Overview As machine learning models are increasingly being employed to aid decision makers in high-stakes settings such as healthcare and criminal justice, it is important to ensure that the decision makers (end users) correctly understand and consequently trust the functionality of these models. This graduate level course aims to familiarize students with the recent advances in the emerging field of interpretable and explainable ML. In this course, we will review seminal position papers of the field, understand the notion of model interpretability and explainability, discuss in detail different classes of interpretable models (e.g., prototype based approaches, sparse linear models, rule based techniques, generalized additive models), post-hoc explanations (black-box explanations including counterfactual explanations and saliency maps), and explore the connections between interpretability and causality, debugging, and fairness. The course will also emphasize on various applications which can immensely benefit from model interpretability including criminal justice and healthcare.
成为VIP会员查看完整内容
0
54

Machine reading comprehension have been intensively studied in recent years, and neural network-based models have shown dominant performances. In this paper, we present a Sogou Machine Reading Comprehension (SMRC) toolkit that can be used to provide the fast and efficient development of modern machine comprehension models, including both published models and original prototypes. To achieve this goal, the toolkit provides dataset readers, a flexible preprocessing pipeline, necessary neural network components, and built-in models, which make the whole process of data preparation, model construction, and training easier.

1
6
下载
预览

Network representation learning in low dimensional vector space has attracted considerable attention in both academic and industrial domains. Most real-world networks are dynamic with addition/deletion of nodes and edges. The existing graph embedding methods are designed for static networks and they cannot capture evolving patterns in a large dynamic network. In this paper, we propose a dynamic embedding method, dynnode2vec, based on the well-known graph embedding method node2vec. Node2vec is a random walk based embedding method for static networks. Applying static network embedding in dynamic settings has two crucial problems: 1) Generating random walks for every time step is time consuming 2) Embedding vector spaces in each timestamp are different. In order to tackle these challenges, dynnode2vec uses evolving random walks and initializes the current graph embedding with previous embedding vectors. We demonstrate the advantages of the proposed dynamic network embedding by conducting empirical evaluations on several large dynamic network datasets.

0
9
下载
预览

Many recommendation algorithms rely on user data to generate recommendations. However, these recommendations also affect the data obtained from future users. This work aims to understand the effects of this dynamic interaction. We propose a simple model where users with heterogeneous preferences arrive over time. Based on this model, we prove that naive estimators, i.e. those which ignore this feedback loop, are not consistent. We show that consistent estimators are efficient in the presence of myopic agents. Our results are validated using extensive simulations.

0
6
下载
预览
小贴士
相关VIP内容
2019年机器学习框架回顾
专知会员服务
27+阅读 · 2019年10月11日
【哈佛大学商学院课程Fall 2019】机器学习可解释性
专知会员服务
54+阅读 · 2019年10月9日
相关资讯
CCF推荐 | 国际会议信息6条
Call4Papers
7+阅读 · 2019年8月13日
CCF推荐 | 国际会议信息10条
Call4Papers
7+阅读 · 2019年5月27日
计算机 | EMNLP 2019等国际会议信息6条
Call4Papers
13+阅读 · 2019年4月26日
已删除
将门创投
4+阅读 · 2019年4月1日
大数据 | 顶级SCI期刊专刊/国际会议信息7条
Call4Papers
7+阅读 · 2018年12月29日
LibRec 精选:推荐系统9个必备数据集
LibRec智能推荐
5+阅读 · 2018年3月7日
人工智能 | 国际会议/SCI期刊约稿信息9条
Call4Papers
3+阅读 · 2018年1月12日
【论文】图上的表示学习综述
机器学习研究会
9+阅读 · 2017年9月24日
【推荐】Python机器学习生态圈(Scikit-Learn相关项目)
机器学习研究会
6+阅读 · 2017年8月23日
相关论文
Directions for Explainable Knowledge-Enabled Systems
Shruthi Chari,Daniel M. Gruen,Oshani Seneviratne,Deborah L. McGuinness
17+阅读 · 2020年3月17日
Heterogeneous Graph Transformer
Ziniu Hu,Yuxiao Dong,Kuansan Wang,Yizhou Sun
21+阅读 · 2020年3月3日
Daniel Adiwardana,Minh-Thang Luong,David R. So,Jamie Hall,Noah Fiedel,Romal Thoppilan,Zi Yang,Apoorv Kulshreshtha,Gaurav Nemade,Yifeng Lu,Quoc V. Le
10+阅读 · 2020年1月27日
Efficiently Embedding Dynamic Knowledge Graphs
Tianxing Wu,Arijit Khan,Huan Gao,Cheng Li
11+阅读 · 2019年10月15日
Anna Rohrbach,Lisa Anne Hendricks,Kaylee Burns,Trevor Darrell,Kate Saenko
3+阅读 · 2019年3月29日
Jindou Wu,Yunlun Yang,Chao Deng,Hongyi Tang,Bingning Wang,Haoze Sun,Ting Yao,Qi Zhang
6+阅读 · 2019年3月28日
dynnode2vec: Scalable Dynamic Network Embedding
Sedigheh Mahdavi,Shima Khoshraftar,Aijun An
9+阅读 · 2018年12月6日
Rem Hida,Naoya Takeishi,Takehisa Yairi,Koichi Hori
7+阅读 · 2018年5月6日
Sven Schmit,Carlos Riquelme
6+阅读 · 2018年3月28日
Hongwei Wang,Fuzheng Zhang,Xing Xie,Minyi Guo
3+阅读 · 2018年1月25日
Top