scholarly journals Learning social networks from text data using covariate information

2021 ◽  
Author(s):  
Xiaoyi Yang ◽  
Nynke M. D. Niezink ◽  
Rebecca Nugent
Keyword(s):  
Social Networks ◽  
Conditional Independence ◽  
Graphical Model ◽  
Text Data ◽  
Graphical Lasso ◽  
Network Recovery ◽  
Covariate Information ◽  
The People ◽  
Historical Figures ◽  
Independence Structure

AbstractAccurately describing the lives of historical figures can be challenging, but unraveling their social structures perhaps is even more so. Historical social network analysis methods can help in this regard and may even illuminate individuals who have been overlooked by historians, but turn out to be influential social connection points. Text data, such as biographies, are a useful source of information for learning historical social networks but the identifcation of links based on text data can be challenging. The Local Poisson Graphical Lasso model models social networks by conditional independence structures, and leverages the number of name co-mentions in the text to infer relationships. However, this method does not take into account the abundance of covariate information that is often available in text data. Conditional independence structure like Poisson Graphical Model, which makes use name mention counts in the text can be useful tools to avoid false positive links due to the co-mentions but given historical tendency of frequently used or common names, without additional distinguishing information, we may introduce incorrect connections. In this work, we therefore extend the Local Poisson Graphical Lasso model with a (multiple) penalty structure that incorporates covariates, opening up the opportunity for similar individuals to have a higher probability of being connected. We propose both greedy and Bayesian approaches to estimate the penalty parameters. We present results on data simulated with characteristics of historical networks and show that this type of penalty structure can improve network recovery as measured by precision and recall. We also illustrate the approach on biographical data of individuals who lived in early modern Britain between 1500 and 1575. We will show how these covariates affect the statistical model’s performance using simulations, discuss how it helps to better identify links for the people with common names and those who are traditionally underrepresented in the biography text data.

Hutton’s Childhood

2018 ◽  
Author(s):  
Susan E. Whyman
Keyword(s):  
Social Networks ◽  
Family Relationships ◽  
Early Life ◽  
Industrial Revolution ◽  
Common Factors ◽  
The People

A newly discovered autobiographical manuscript is used to reconstruct Hutton’s early life in Derby and Nottingham. Of the data in his ‘Memorandums from Memory all Trifles and, of Ancient Date’, 70 per cent was not included in his published Life. This chapter analyses the people, places, and subjects found in this manuscript. Hutton’s earliest memories reveal his hardships as a child labourer in a Derby silk mill and an apprentice stockinger in Nottingham. We observe the strategies he used to find a pathway out of poverty, and the details of his self-education. The importance of family relationships, social networks, and urban marketplaces were common factors shared by entrepreneurs in the Industrial Revolution. How Hutton prepared to become a bookseller is also revealed.

scholarly journals Information Asymmetry and Trust: A Framework for Studying Microfinance in India

2005 ◽  
Vol 30 (4) ◽  
pp. 77-86 ◽  
Author(s):  
M S Sriram
Keyword(s):  
Social Networks ◽  
Transaction Costs ◽  
Rural Areas ◽  
Financial Services ◽  
Imperfect Information ◽  
Informal Networks ◽  
The Poor ◽  
The People ◽  
Financial Transactions

In recent times, microfinance has emerged as a major innovation in the rural financial marketplace. Microfinance largely addresses the issue of access to financial services. In trying to understand the innovation of microfinance and how it has proved to be effective, the author looks at certain design features of microfinance. He first starts by identifying the need for financial service institutions which is basically to bridge the gap between the need for financial services across time, geographies, and risk profiles. In providing services that bridge this gap, formal institutions have limited access to authentic information both in terms of transaction history and expected behaviour and, therefore, resort to seeking excessive information thereby adding to the transaction costs. The innovation in microfinance has been largely to bridge this gap through a series of trustbased surrogates that take the transaction-related risks to the people who have the information — the community through measures of social collateral. In this paper, the author attempts to examine the trajectory of institutional intermediation in the rural areas, particularly with the poor and how it has evolved over a period of time. It identifies a systematic breach of trust as one of the major problems with the institutional interventions in the area of providing financial services to the poor and argues that microfinance uses trust as an effective mechanism to address one of the issues of imperfect information in financial transactions. The paper also distinguishes between the different models of microfinance and identifies which of these models use trust in a positivist frame and as a coercive mechanism. The specific objectives of the paper are to: Superimpose the role of trust in various types of exchanges and see how it impacts the effectiveness of repeated transactions. While greater access to information fosters trust and thus helps social networks to reduce transaction costs, there could be limits to which exchanges could solely depend on networks and trust. Look at the frontiers where mutual trust cannot work as a surrogate for lower appraisal costs. Use an example in the Canadian context and see how an entity that started on the basis of social networks and trust had to morph into using the techniques used by other formal nonneighbourhood institutions as it grew in size and went beyond a threshold. Using the Canadian example, the author argues that as the transactions get sophisticated, it is possible to achieve what informal networks have achieved through the creative use of information technology. While we find that the role of trust both in the positivist and the coercive frame does provide some interesting insights into how exchanges with the poor could be managed, there still could be breaches in the assumptions. This paper identifies the conditions under which the breaches could possibly happen and also speculates on the effect of such breaches.

scholarly journals THE ISLAMIC CULTURE OF “WETU TELU ISLAM” AFFECTING SOCIAL RELIGION IN LOMBOK

2020 ◽  
Vol 22 (1) ◽  
pp. 97-115
Author(s):  
Muliadi Muliadi ◽  
Didin Komarudin
Keyword(s):  
Religious Culture ◽  
Cultural Patterns ◽  
Islamic Culture ◽  
Religious Rituals ◽  
Religious System ◽  
The People ◽  
Historical Figures ◽  
History Of

This writing is motivated by a very abundant religious culture in Indonesia, including the phenomenon found in Lombok, West Nusa Tenggara which is famous for “Wetu Telu Islam”. It contains the religious system filled with ceremonies and rituals which are accompanied by special symbols that have certain meanings. The method used in this paper is historical descriptive, by systematically explaining the history of the people of Lombok, the cultural patterns of “Wetu Telu Islam”, including its historical figures, doctrine, development, and existence. Then the writer uses structural semiology in analyzing the meaning of symbol elements found in the religious rituals of “Wetu Telu Islam” in Lombok. “Wetu Telu Islam” according to the people of Lombok is a very perfect Islam as it is built from two solid dimensions, namely dzohir and ihsan. For that reason, “Wetu Telu Islam” for them is the teachings of Sufism which emphasize the spirit, and soul. It is the spirit of holistic Islamic teachings, namely: shari’a, thoriqot, haqiqot, and ma‘rifat. Everything is building up, mutually reinforcing, and inseparable.Tulisan ini bermuara dari budaya agama yang sangat berlimpah di Indonesia, termasuk fenomena yang ditemukan di Lombok, Nusa Tenggara Barat yang terkenal dengan “Islam Wetu Telu”. Sistem keagamaan yang terkandung di dalamnya sarat upacara dan ritual yang disertai simbol-simbol khusus bermakna tertentu. Metode yang digunakan dalam makalah ini adalah deskriptif historis, yaitu secara sistematis menjelaskan sejarah masyarakat Lombok, pola-pola budaya “Islam Wetu Telu”, termasuk tokoh sejarah, doktrin, perkembangan dan keberadaannya. Kemudian penulis menggunakan semiologi struktural dalam menganalisis makna elemen simbol yang ditemukan dalam ritual keagamaan “Islam Wetu Telu”di Lombok. “Islam Wetu Telu” menurut masyarakat Lombok adalah Islam yang sangat sempurna karena dibangun dari dua dimensi yang kuat, yaitu dzohir dan ihsan. Karena itu, “Islam Wetu Telu” bagi mereka adalah ajaran tasawuf yang menekankan hati dan jiwa. Ini adalah semangat ajaran Islam holistik, yaitu: syariah, thoriqot, haqiqot, dan ma’rifat. Semuanya membangun, saling menguatkan, dan tak terpisahkan.

scholarly journals Determining the proximity of groups in social networks based on text analysis using big data

2019 ◽  
pp. 521-526
Author(s):  
A S Mukhin ◽  
I A Rytsarev ◽  
R A Paringer ◽  
A V Kupriyanov ◽  
D V Kirsh
Keyword(s):  
Social Networks ◽  
Big Data ◽  
Social Network ◽  
Data Collection ◽  
Text Analysis ◽  
Software Tool ◽  
Text Data ◽  
The Social ◽  
Information Research ◽  
Definition Of

The article is devoted to the definition of such groups in social networks. The object of the study was selected data social network Vk. Text data was collected, processed and analyzed. To solve the problem of obtaining the necessary information, research was conducted in the field of optimization of data collection of the social network Vk. A software tool that provides the collection and subsequent processing of the necessary data from the specified resources has been developed. The existing algorithms of text analysis, mainly of large volume, were investigated and applied.

THE EMOTION OF JOY IN SOCIAL NETWORKS: VERBAL, PARAVERBAL AND NONVERBAL FORMS OF EXPRESSION

2021 ◽  
Author(s):  
A.V. Kolmogorova ◽  
S.R. Akhmadeeva
Keyword(s):  
Social Networks ◽  
Comparative Analysis ◽  
Team Sport ◽  
Sport Performance ◽  
Emotion Expression ◽  
The Internet ◽  
Text Data ◽  
Gender Factor

The article explores the text data of the Internet-comments published on social networks by fans to celebrate the victory of their favorite sportsmen. The aim of the publication is to analyze verbal, paraverbal and nonverbal forms of emotion expression in two groups of fans: those who are keen on sports profiling typically masculine properties (strength, audacity, endurance), and, on the contrary, those who are passionate about the sport performance featuring feminine characteristics (grace, beauty, flexibility). The conducted comparative analysis gives evidence about the presence of a number of specific features due to the effect of gender factor. However, this factor largely correlates with other variables, such as linguacultural patterns, the nature of the sport itself (team sport vs individual sport).

scholarly journals Regularized Within-Class Precision Matrix Based PLDA in Text-Dependent Speaker Verification

2020 ◽  
Vol 10 (18) ◽  
pp. 6571 ◽  
Author(s):  
Sung-Hyun Yoon ◽  
Jong-June Jeon ◽  
Ha-Jin Yu
Keyword(s):  
Conditional Independence ◽  
Speaker Verification ◽  
Equal Error Rate ◽  
Estimation Errors ◽  
Precision Matrix ◽  
Linear Discriminant ◽  
Selection Operator ◽  
Independence Structure ◽  
Empirical Covariance ◽  
Text Dependent Speaker Verification

In the field of speaker verification, probabilistic linear discriminant analysis (PLDA) is the dominant method for back-end scoring. To estimate the PLDA model, the between-class covariance and within-class precision matrices must be estimated from samples. However, the empirical covariance/precision estimated from samples has estimation errors due to the limited number of samples available. In this paper, we propose a method to improve the conventional PLDA by estimating the PLDA model using the regularized within-class precision matrix. We use graphical least absolute shrinking and selection operator (GLASSO) for the regularization. The GLASSO regularization decreases the estimation errors in the empirical precision matrix by making the precision matrix sparse, which corresponds to the reflection of the conditional independence structure. The experimental results on text-dependent speaker verification reveal that the proposed method reduce the relative equal error rate by up to 23% compared with the conventional PLDA.

HIGH-ORDER CONDITIONAL DISTANCE COVARIANCE WITH CONDITIONAL MUTUAL INDEPENDENCE

2020 ◽  
pp. 1-18
Author(s):  
Pengfei Liu ◽  
Xuejun Ma ◽  
Wang Zhou
Keyword(s):  
Linear Combination ◽  
Conditional Independence ◽  
Graphical Model ◽  
High Order ◽  
Gaussian Graphical Model ◽  
Random Vectors ◽  
Independence Test ◽  
Mutual Independence ◽  
Simulation Results ◽  
Distance Covariance

We construct a high-order conditional distance covariance, which generalizes the notation of conditional distance covariance. The joint conditional distance covariance is defined as a linear combination of conditional distance covariances, which can capture the joint relation of many random vectors given one vector. Furthermore, we develop a new method of conditional independence test based on the joint conditional distance covariance. Simulation results indicate that the proposed method is very effective. We also apply our method to analyze the relationships of PM2.5 in five Chinese cities: Beijing, Tianjin, Jinan, Tangshan and Qinhuangdao by the Gaussian graphical model.

The 2004 GSS Finding of Shrunken Social Networks: An Artifact?

2009 ◽  
Vol 74 (4) ◽  
pp. 657-669 ◽  
Author(s):  
Claude S. Fischer
Keyword(s):  
Social Networks ◽  
Social Isolation ◽  
General Social Survey ◽  
Network Data ◽  
Technical Error ◽  
Social Survey ◽  
The People

McPherson, Smith-Lovin, and Brashears (2006, 2008b) reported that Americans' social networks shrank precipitously from 1985 to 2004. When asked to list the people with whom they discussed “important matters,” respondents to the 2004 General Social Survey (GSS) provided about one-third fewer names than did respondents in the 1985 survey. Critically, the percentage of respondents who provided no names at all increased from about 10 percent in 1985 to about 25 percent in 2004. The 2004 results contradict other relevant data, however, and they contain serious anomalies; this suggests that the apparently dramatic increase in social isolation is an artifact. One possible source of the artifact is the section of the 2004 interview preceding the network question; it may have been unusually taxing. Another possible source is a random technical error. With as yet no clear account for these inconsistencies and anomalies, scholars should be cautious in using the 2004 network data. Scholars and general readers alike should draw no inference from the 2004 GSS as to whether Americans' social networks changed substantially between 1985 and 2004; they probably did not.

Sign in / Sign up

Export Citation Format

Share Document