SEMOGRAPH Information System as a Platform for Network-Based Linguistic Research: A Case Study of Verbal Behavior of Social Network Users

Baranov, Dmitry; Белоусов, Константин; Erofeeva, Elena V.; Leshchenko, Yuliya

doi:10.1007/978-981-13-8260-4_29

Cited by 4 publications

(3 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Semograph has a high-level graphical user interface with which the user can both manually and automatically work with text data, studying their semantic properties. Analyzing textual data based on semantic fields and semantic components reveals its semantic structure that is an important part of linguistic research [26,27].…”

Section: Related Workmentioning

confidence: 99%

Creative Map Studio: A Platform for Visual Analytics of Mental Maps

Chumakov¹,

Ryabinin²,

Белоусов³

et al. 2021

View full text Add to dashboard Cite

This paper is devoted to the development of software tools, which allow to create and analyze mental maps in digital format. Mental maps are used to study humans' cognitive characteristics and geospatial perception. To support Digital Humanities research based on the analysis of the mental maps, we developed a special high-level web-based vector graphics editor called Creative Maps Studio that allows informants to intuitively draw digital naive maps as a representation of their mental maps.The Creative Maps Studio web application provides a wide variety of drawing tools based on points, lines, and areas, which allow representing different objects on the map, such as cities, historical monuments, industrial facilities, state borders, roads, rivers, steppes, seas, swamps, etc. For each object, individual parameters can be set, such as color, size, transparency, name, description, emoticons, etc.Digital maps can be analyzed in various ways, relying on computer vision, machine learning, visualization, and manual expert analysis. Creative Maps Studio stores not only the final state of maps but also the entire history of user actions on the canvas, which makes it possible to consider the process of creating a map by the analysis.While Creative Maps Studio provides basic functions to view the informants' maps and the history of their creation, we propose involving special software to achieve a comprehensive analysis of mental maps. In particular, we rely on the previously developed SciVi data mining platform and Semograph graph-semantic modeling information system. Creative Maps Studio provides appropriate export capabilities to transfer required data to these software systems. After exporting, the expert can use SciVi and Semograph to perform visual analytics of map objects' properties, to handle maps' textual layers, and to classify the maps on the principles of the fuzzy set theory. Thus, the mentioned software can be used to carry out the comprehensive study of informants' spatial perception.In the future works, we plan to expand the set of objects available to draw the maps, allowing researchers to create custom ones, as well as to integrate analytics tools of maps creation history directly in the Creative Maps Studio.

show abstract

Section: Related Workmentioning

confidence: 99%

Creative Map Studio: A Platform for Visual Analytics of Mental Maps

Chumakov¹,

Ryabinin²,

Белоусов³

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Analysis of the verbal associations (naive maps verbal level) was performed with the help of graphosemantic simulation using SEMO-GRAPH Information System (http://semograph.org), meant to reveal connections between units of the information space of the text or texts selection (learn more about how to work with texts using SEMOGRAPH Information System (Baranov et al, 2019;Belousov et al, 2017).…”

Section: Geoconcept Moscow Through Collective Regional Visionmentioning

confidence: 99%

Naive geography: geoconceptology and topology of geomental maps

Зелянская

Белоусов

Galinskaia

et al. 2020

Heliyon

View full text Add to dashboard Cite

The article presents the study of the geospace mental representations and their variability depending on the regional point of view. The research material comprises about 500 naive maps of Russia, created by informants of seven Russian regions: Moscow, St. Petersburg (capitals), Siberia (Barnaul, Biysk), Southern, Mid- and Northern Ural (Orenburg, Ufa, Perm) and Kaliningrad. A geoconcept, as a set of collective ideas about a geographic object, synthesizes images of a geographic location (topos), its name (toponym), ideas about it and its spatial parameters (length, coordinates, location relative to other geolocations). The paper raises the problem of the topology of the mental space, and describes the method and results of constructing computable metric models of geomental spaces. The use of modern means of processing and analyzing naive maps allowed to detect spatial dependencies between geoconcepts, their probable localization zones, and position relative to each other on the geomental map space. Modeling of geoconcepts was carried out on the example of the analysis of the collective regional representations associated with the capital (Moscow). Noticeable differences were found in the regional geoconcepts of Moscow, which makes it relevant to conduct research on the regional variability of the geoconcept systems of the country's common space.

show abstract

“…This formulation of the hypothesis poses the problem of analyzing text arrays consisting of user-generated content from social media. The problem is solved by using the information system of graphosemantic modeling "Semograph" [5] developed by the team. The cornerstone of "Semograph" is a concept of semantic fields -sets of linguistic units (words, phrases and even more compound constructions) with meanings that share common semantic feature.…”

Section: Introductionmentioning

confidence: 99%

Social Media User Profiling Based on Genre Extraction

Белоусов

Labutin

2021

Frontiers in Artificial Intelligence and Applications

Self Cite

View full text Add to dashboard Cite

The task of automatic user profiling (in particular, determining their psychological parameters from their texts) in Social Networking Services (SNS) is of great practical importance in many fields (PR and marketing, advertising, politics, social relations and recommendations, etc.). However, this problems’ solution is often complicated by the need to process large amounts of data and the inability to explain the results achieved. Our article presents a new extensible fuzzy classification method for social media user profiling based on preliminary expert analysis of the linguistic behavior of such users. The proposed method is akin to topic modelling, but is not computationally expensive (so it can be used for large-scale data / web text analysis) and produces results that are relatively easy to interpret. Comparison with the other methods presented in literature also testifies in favor of the approach. The profiling accuracy reaches 65–70% on a relatively small dataset for such kind of studies.

show abstract

SEMOGRAPH Information System as a Platform for Network-Based Linguistic Research: A Case Study of Verbal Behavior of Social Network Users

Cited by 4 publications

References 3 publications

Creative Map Studio: A Platform for Visual Analytics of Mental Maps

Creative Map Studio: A Platform for Visual Analytics of Mental Maps

Naive geography: geoconceptology and topology of geomental maps

Social Media User Profiling Based on Genre Extraction

Contact Info

Product

Resources

About