Analysis of News Flow Dynamics Based on the Company Co-mention Network Characteristics

Balash, Vladimir; Chekmareva, Alfia; Faizliev, Alexey; Sidorov, Sergei; Mironov, Sergei V.; Volkov, Daniil

doi:10.1007/978-3-030-05414-4_42

Cited by 2 publications

(7 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Figure 6a shows that the local structure of the market graph is stable over time. During the financial crisis of 2008 (periods [38][39][40][41][42][43][44][45][46][47][48][49][50], the topological dissimilarity increases significantly and quickly returns to its previous level. Redundancy analysis shows that 56% of the variance is explained by the first principal component which is good enough.…”

Section: Multidimensional Scalingmentioning

confidence: 99%

“…Various important characteristics of company co-mention networks were studied with use of different SNA metrics, such as eigenvector centrality, degree of centrality, betweenness centrality, closeness centrality, frequency, etc. in papers [38,39], and key companies of networks were found. It was demonstrated that the degree distributions as well as the clustering-degree of the analyzed graphs follow a power law, but using a non-typical exponent value.…”

Section: Introductionmentioning

confidence: 97%

“…• Some researchers believed that a connection between companies arises, if both companies have common members of the board of directors [33][34][35][36][37]. • Several papers dealt with company co-mention networks in which connection between companies is reflected by the fact of mentioning the both companies in one news item [38][39][40][41]. • Also, in various applications it can be useful to build graphs of industrial or spatial affiliation of companies [40].…”

Section: Introductionmentioning

confidence: 99%

“…Following ideas of [38,39] the current paper presents a company co-mention network as a graph where the world's major companies mentioned in financial, business-related, and economic news flow are shown as nodes. If any two companies are mentioned in the same piece of news, the company co-mentions graph shows it as the edge between two nodes.…”

Section: Introductionmentioning

confidence: 99%

“…The QAP analysis method was used in [40] to examine the correlations between the company co-mention network and graphs, describing sectoral (and spatial) affiliation. Papers [38,39] explore how the structural characteristics of the company co-mentions graph change over time, such as the distribution of the vertices degrees, the distribution of the average clustering coefficient, the edge density, the size of maximum clique, its connectivity. It was found that the power-law structure of the co-mention graph is quite stable.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Stability Analysis of Company Co-Mention Network and Market Graph Over Time Using Graph Similarity Measures

Faizliev

Balash

Petrov

et al. 2019

Journal of Open Innovation: Technology, Market, and Complexity

Self Cite

View full text Add to dashboard Cite

The aim of the paper is to provide an analysis of news and financial data using their network representation. The formation of network structures from data sources is carried out using two different approaches: by building the so-called market graph in which nodes represent financial assets (e.g., stocks) and the edges between nodes stand for the correlation between the corresponding assets, by constructing a company co-mention network in which any two companies are connected by an edge if a news item mentioning both companies has been published in a certain period of time. Topological changes of the networks over the period 2005–2010 are investigated using the sliding window of six-month duration. We study the stability of the market graph and the company co-mention network over time and establish which of the two networks was more stable during the period. In addition, we examine the impact of the crisis of 2008 on the stability of the market graph as well as the company co-mention network. The networks that are considered in this paper and that are the objects of our study (the market graph and the company co-mention network) have a non-changing set of nodes (companies), and can change over time by adding/removing links between these nodes. Different graph similarity measures are used to evaluate these changes. If a network is stable over time, a measure of similarity between two graphs constructed for two different time windows should be close to zero. If there was a sharp change between the graphs constructed for two adjacent periods, then this should lead to a sharp increase in the value of the similarity measure between these two graphs. This paper uses the graph similarity measures which were proposed relatively recently. In addition, to estimate how the networks evolve over time we exploit QAP (Quadratic Assignment Procedure). While there is a sufficient amount of works studying the dynamics of graphs (including the use of graph similarity metrics), in this paper the company co-mention network dynamics is examined both individually and in comparison with the dynamics of market graphs for the first time.

show abstract

Section: Multidimensional Scalingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 97%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Stability Analysis of Company Co-Mention Network and Market Graph Over Time Using Graph Similarity Measures

Faizliev

Balash

Petrov

et al. 2019

Journal of Open Innovation: Technology, Market, and Complexity

Self Cite

View full text Add to dashboard Cite

show abstract

Application of Methods of Statistical Analysis of Network Structures to Study the Dynamics of Market Graphs and Graphs of Joint References

Balash¹,

Sidorov²,

Faizliev³

2019

I.I.I

View full text Add to dashboard Cite

Аннотация. В данной статье рассматриваются приложения методов анализа сетевых структур для исследования динамики процессов ценообразования на финансовых рынках и их отражением в новостных потоках. Представление взаимодействий между социально-экономическими явлениями в виде сети или графа позволяет не только повысить наглядность отображения структуры взаимосвязей, но и проводить статистический анализ свойств такого графа и делать обоснованные выводы о сходстве или различии структуры связей в разные периоды времени. Целями нашего исследования являлось, во-первых, анализ изменения во времени свойств графов двух параллельно протекающих процессов, и, во-вторых, сходства или различия их динамики, в-третьих, насколько результаты анализа устойчивы относительно выбора метрики сходства графов. Мы предполагаем, что влияние всей совокупности скрытых, ненаблюдаемых факторов, воздействующих на процессы ценообразования на финансовых рынках, должно находить свое отражение в изменениях структурных свойств, так называемых рыночных графов и графов совместных упоминаний компаний в новостных потоках. Рыночный граф, описывает сеть взаимодействий между доходностями активов, вершинами которого являются компании, акции которых котируются на биржах, соединяемых ребрами, если показатель тесноты связи между доходностями акций за выбранный период превосходит по абсолютной величине выбранный порог. Использование данных провайдеров новостной аналитики позволяет также оценить частоту совместных упоминаний компаний в финансовых новостях. Сдвигая начало сегмента на шаг, равный одному дню, месяцу и т. д., мы получали последовательность матриц смежности графов. Для изучения стабильности и изменчивости структурных свойств подобных графов мы применяли QAP-процедуру корреляционного и регрессионного анализа между матрицами смежности и анализ сходства топологий сетевых структур в разные отрезки времени. Результаты применения методов многомерного шкалирования для состояний динамических графов с использованием двух различных метрик сходства сетевых структур, отражающих изменение меры центральности узлов сети и топологии сети приводят к выводу, что однофакторная модель в состоянии объяснить существенную часть динамики изменений структуры как рыночного графа, так и графа соупоминаний.

show abstract

Analysis of News Flow Dynamics Based on the Company Co-mention Network Characteristics

Cited by 2 publications

References 25 publications

Stability Analysis of Company Co-Mention Network and Market Graph Over Time Using Graph Similarity Measures

Stability Analysis of Company Co-Mention Network and Market Graph Over Time Using Graph Similarity Measures

Application of Methods of Statistical Analysis of Network Structures to Study the Dynamics of Market Graphs and Graphs of Joint References

Contact Info

Product

Resources

About