A System for Analysis of Big Data from Social Media

Lande, Dmytro; Subach, Igor; Puchkov, A. V.

doi:10.11610/isij.4703

Cited by 8 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After the theory was proposed, a seminar on multimedia picture language was held at Tianjin Normal University. Since picture art design before that mostly applied to other disciplines of art theories, Lande et al proposed a multimedia picture language art theory, which solved the problem of borrowing other disciplines of art theories [9]. After that, Li combined multimedia picture art theory with cognitive psychology to study the cognitive law of multimedia picture language and explored the cognitive law that should be followed in the design of multimedia teaching resources [10].…”

Section: Current Status Of Researchmentioning

confidence: 99%

Optimization of Hybrid Multimedia Art and Design Teaching Mode in the Era of Big Data

Tian

2021

Scientific Programming

View full text Add to dashboard Cite

In this paper, a 9-layer convolutional neural network with 4 convolutional layers, 4 pooling layers, and 1 fully connected layer is designed to recognize the emotions of digital learning images in the era of big data. The convolutional neural network is trained using digital learning images that have been labeled with emotions, and the final test shows that the network has good recognition results. This in turn causes the information overload problem to arise. And combined with the questionnaire results and interviews, it was found that there are problems of technology for technology’s sake, teaching for teaching’s sake, and in multimedia teaching, and these will add to the psychological and visual sensory burden of students and easily cause the information overload problem. The types of information overload problems in multimedia-assisted teaching are summarized as follows: unreasonable presentation of information, which causes audiovisual redundancy; too much teaching irrelevant information, which increases the external cognitive load; and an uncoordinated audiovisual environment, which increases the external cognitive load. Starting from the perspective of the integration of preservice to in-service art teachers’ new media art curriculum design and teaching ability development, three representative teacher education cases were studied using a combination of teaching practice and case tracking methods to summarize the successful experiences and effective ways of art teachers’ new media art curriculum development and teaching ability development, which will provide future art teacher training and in-service teachers’ professional development. Both are below 5%. The types of funny emotions are mainly distributed in animation teaching methods. Animation resources are generally well designed in color and layout and can convey good visual emotional characteristics. In other types of images, the emotional distribution level of funny is less than 10%. It is worthwhile to learn from this experience.

show abstract

Section: Current Status Of Researchmentioning

confidence: 99%

Optimization of Hybrid Multimedia Art and Design Teaching Mode in the Era of Big Data

Tian

2021

Scientific Programming

View full text Add to dashboard Cite

show abstract

“…The prerequisite for the creation of the method was that the authors have at their disposal full-text databases of documents collected from social networks using the CyberAggregator system. 4 Each of these documents is assigned so-called reference terms, a predetermined number of the most significant terms defined by the CHVG method. 5 It is supposed that, on a request to the CyberAggregator system, the corresponding thematic information array of documents is formed, on the basis of which the network of terms should be constructed and automatically grouped by topics as a model of subject area and the most significant in some sense documents should be selected, whose content should constitute the digest.…”

Section: Groundingmentioning

confidence: 99%

“…To solve this problem, we propose an approach ideologically close to the well-known TF-IDF approach, 6 used in the theory of information retrieval. Accordingly, for this approach, the definition of the weight of each term can be given as the product of some non-decreasing function of the absolute frequency of its occurrence and the number of terms from the set T, which this term is not related to (not included in the same documents):…”

Section: Groundingmentioning

confidence: 99%

“…At the same time, as practice shows, the given approach solves well the problem of clustering a network of terms within the framework of the CyberAgregator system. 4 The CyberAgregator system is designed to collect, search and analyze information from social networks and websites on cybersecurity issues. Search and data aggregation in this system is provided by Elasticsearch tools.…”

mentioning

confidence: 99%

See 1 more Smart Citation

A Clustering Method for Information Summarization and Modelling a Subject Domain

Lande¹,

Subach²,

Puchkov³

et al. 2021

ISIJ

Self Cite

View full text Add to dashboard Cite

The article presents a discriminant cluster analysis method used to form realtime models of subject areas and digests based on automatic analysis of a large number of messages from social networks. It is based on estimating the discriminant value of terms. Cluster analysis, like the well-known LSA algorithm, provides a matrix representation of the data. The novelty is in using the most significant discriminant values as centroids to define clusters.The algorithm is simplified; it does not involve referencing to the adjacency matrix, definition of eigenvectors. Its complexity is O(N2), where K is the number of clusters and N -the number of reference terms. If it is necessary to improve the quality of the proposed approach, the defined centroids can be transferred as input data for other known algorithms. Based on the above algorithm, toolkits for the formation of a language network and digests were developed and embedded in the "CyberAggregator" system, which provides accumulation, processing, summarization of data from social networks on cybersecurity issues.

show abstract

“…The fractal properties of thematic information flow from the Internet are discussed in [16], and, as a database for a computational experiment, the network news monitoring system InfoStream was chosen. The method of calculating Hurst indicators for the cluster defined by the subject of the query is presented and a qualitative interpretation of the results is given.…”

mentioning

confidence: 99%

Method of Distinguishing Styles by Fractal and Statistical Indicators of the Text as a Sequence of the Number of Letters in Its Words

et al. 2021

View full text Add to dashboard Cite

The method of the analysis of different texts styles is developed in the paper. Integer numerical sequences are used as models. The elements of the sequence are the number of letters in the words of the text. The algorithm for calculating the exact value of the fractal dimension is developed. It provides the determination of the exact value of the Hurst index. The value of the power dependence constant is calculated. The obtained indicators in the aspect of fractality completely describe the objects of research.

show abstract

A System for Analysis of Big Data from Social Media

Cited by 8 publications

References 14 publications

Optimization of Hybrid Multimedia Art and Design Teaching Mode in the Era of Big Data

Optimization of Hybrid Multimedia Art and Design Teaching Mode in the Era of Big Data

A Clustering Method for Information Summarization and Modelling a Subject Domain

Method of Distinguishing Styles by Fractal and Statistical Indicators of the Text as a Sequence of the Number of Letters in Its Words

Contact Info

Product

Resources

About