Huge Amount Of Data Research Articles

Prediction model of middle school student performance based on MBSO and MDBO-BP-Adaboost method

Predictions of student performance are important to the education system as a whole, helping students to know how their learning is changing and adjusting teachers' and school policymakers' plans for their future growth. However, selecting meaningful features from the huge amount of educational data is challenging, so the dimensionality of student achievement features needs to be reduced. Based on this motivation, this paper proposes an improved Binary Snake Optimizer (MBSO) as a wrapped feature selection model, taking the Mat and Por student achievement data in the UCI database as an example, and comparing the MBSO feature selection model with other feature methods, the MBSO is able to select features with strong correlation to the students and the average number of student features selected reaches a minimum of 7.90 and 7.10, which greatly reduces the complexity of student achievement prediction. In addition, we propose the MDBO-BP-Adaboost model to predict students' performance. Firstly, the model incorporates the good point set initialization, triangle wandering strategy and adaptive t-distribution strategy to obtain the Modified Dung Beetle Optimization Algorithm (MDBO), secondly, it uses MDBO to optimize the weights and thresholds of the BP neural network, and lastly, the optimized BP neural network is used as a weak learner for Adaboost. MDBO-BP-Adaboost After comparing with XGBoost, BP, BP-Adaboost, and DBO-BP-Adaboost models, the experimental results show that the R2 on the student achievement dataset is 0.930 and 0.903, respectively, which proves that the proposed MDBO-BP-Adaboost model has a better effect than the other models in the prediction of students' achievement with better results than other models.

Hybrid Deep Learning Model to Predict Students’ Sentiments in Higher Educational Institutions

Sentiment analysis has been widely used in various fields of social media, education, and business. Specifically, in the education domain, the usage of sentiment analysis is difficult due to the huge amount of information, the nature of language, and processing the diverse perceptions of students. Deep learning emerges as an advanced concept in the realm of machine learning that learns features automatically from raw text data, making them well-suited for sentiment analysis tasks. In recent years, deep learning has been used in analyzing the sentiments. Deep learning architectures have surpassed other machine learning paradigms for performing sentiment analysis. The ability to analyze automatically the students’ sentiments enables HEI to process huge amounts of unstructured data quickly, efficiently, and cost-effectively. The paper aims to predict the sentiments of students’ reviews posted in VLE regarding online learning that enables the educators to optimize their teaching methods for the best results. This study paper explores the usage of CNN, LSTM, and hybrid CNN-LSTM for the prediction of sentiments. The proposed hybrid CNN-LSTM architecture achieves superior performance compared to other baseline algorithms with respect to accuracy, precision, recall, and F1 score. According to outcomes, the recommended technique achieves remarkable accuracy of 97%. The findings facilitate the progress of a more efficient deep learning sentiment prediction system that gives valuable insights from a huge volume of students’ textual data.

Synthetic satellite telemetry data for machine learning

AbstractFor many machine learning tasks, labeled data are crucial. Even though there are methods that can be trained with data with only few labels, most of the tasks require many labels. In satellite operations, a huge amount of data are generated by the telemetry parameters of a satellite that keep track of its status. Modern satellites collect telemetry data of thousands of parameters. For example, the GRACE Follow-On satellites, operated by the German Space Operations Center (GSOC) at the German Aerospace Center (DLR), define about 80,000 unique housekeeping parameters each. However, all these telemetry data lack a complete/holistic set of labels. These data are usually unpredictable, hard to reproduce, and very diverse. As a consequence, expert knowledge is necessary to label these data, e.g., with anomalies. Moreover, labeling data by hand can be very time-consuming and, therefore, expensive. To overcome these obstacles, we implemented a synthetic satellite telemetry data library that is able to (a) generate a large variety of telemetry-like data, (b) add a plethora of well-defined anomalies to these data, and (c) deliver the labels for these injected anomalies. With these data, we are now able to train, validate, and test our machine learning models. Furthermore, we can compare different models with reproducible data. Since satellite telemetry data are often strictly confidential, we can share these synthetic data easily with our research partners.

Brain Glial Cell Tumor Classification through Ensemble Deep Learning with APCGAN Augmentation

Classification of brain tumor plays a vital role in medical imaging for accurate diagnosis, treatment, and monitoring. Deep learning approaches have gained significant traction in this industry because of their ability to extract relevant features from medical images. The research suggests employing an ensemble classifier with a weighted voting mechanism to categorize glial cell brain malignancies such as Astrocytoma, Glioblastoma multiforme, Oligodendroglioma, and Ependymoma. The proposed ensemble technique employs three main classifiers: Convolutional Neural Network (CNN), Deep Convolutional Long Short Term Memory (C-LSTM), and Deep Convolutional Neural Network + Conditional Random Fields (DCNN+CRF). Deep learning algorithms require a huge amount of input data to avoid overfitting. The Adaptive Progressive Convolutional Generative Adversarial Networks (APCGANs) are used to produce realistic artificial images to efficiently train the proposed methodology. Overall, the proposed ensemble method with weighted voting strategy consistently outperforms the other tested algorithms (CNN, C-LSTM, and DCNN+CRF). Ensemble method attained an accuracy of 99.4 %, recall - 99.1%, precision- 98.0%, and F1-score of 99.2%. Ensemble method consistently demonstrates superior performance in accurately classifying brain tumors, making it a promising algorithm for brain tumor analysis tasks.

Neutrosophic Sets in Big Data Analytics: A Novel Approach for Feature Selection and Classification

Big Data Analytics are said to help in transforming huge amounts of raw data towards valuable information that can be used, but there are formidable challenges in feature selection and classification due to the complexity and high dimensionality of the data. Traditional methods are usually too weak to handle the built-in uncertainty, imprecision, and inconsistency within big data and they often fail to perform well. This paper aims to induce the new methodology on these problems using the sets of neutrosophic in dealing with more flexible and nuanced data analysis. The key contributions to the current approach proposed are threefold. First, generalization of the classical set through extension of the notions of truth, indeterminacy, and falsity by allowing representations of uncertainty in data. The second combines a powerful process for selecting features based upon neutrosophic set theory that is optimal by genetic algorithms and advances a step further by applying these features in training and validating the classification models across a set of different domains. Therefore, the major aim from this study is to increase accuracy and reliability in feature selection and classification in big data analytics. This methodology has been implemented and tested over datasets of the following types: healthcare, finance, social media, and more. Results have proved great improvement against conventional performance metrics, for example, the classification accuracy with an SVM classifier over the Cleveland Heart Disease dataset increases from 83.5% to 87.2%, and of a Random Forest classifier over a financial dataset from 76.4% to 81.9%. For instance, the accuracy of social media sentiment analysis changed to 82.7% from 78.3%. All these findings establish that the neutrosophic set-based method holds good advantages in addressing the limitations of classical alternatives. The proposed approach of neutrosophism, through an explicit model, enhances performances in classifications and, at the same time, augments overall robustness and reliability in big data analytic. The importance of this study lies in establishing the groundwork for further research and practical applications, thus indicating possible further development in this field.

Evaluation of User Activity Parameters in Social Networks Using Machine Learning Tools

Social networks provide a huge amount of data that can be used to understand user behavior because they cover a wide range of human activities such as posts, comments, likes and follower interactions. Analyzing these data helps to identify patterns and trends that can shape patterns of behavior and assess the parameters of their activity. Key parameters such as the frequency of users' actions, their interactions, the content they share, and the emotional tone of their communications offer valuable insights into user behavior. By formalizing these parameters, large data sets can be turned into meaningful indicators for analyzing behavior, predicting or improving existing models by using machine learning tools, namely: regression methods or by applying their classification. To improve the accuracy of the analysis, it is extremely important to choose appropriate activity indicators and take into account changes over time and different types of interactions. This research suggests analyzing key metrics, including post frequency and user engagement, and visualizing these metrics to gain a deeper understanding of user behavior trends. According to the obtained results, it is possible to calculate the audience engagement factor, the popularity factor of the post in social networks, and the audience retention rate. In addition, an important result when evaluating user parameters for analyzing their behavior is the content influence factor, which shows the contribution of a user's post to other users

Progressive Bounded Error Piecewise Linear Approximation with Resolution Reduction for Time Series Data Compression

Today, huge amounts of time series data are sensed continuously by AIoT devices, transmitted to edge nodes, and to data centers. It costs a lot of energy to transmit these data, store them, and process them. Data compression technologies are commonly used to reduce the data size and thus save energy. When a certain level of data accuracy is sacrificed, lossy compression technologies can achieve better compression ratios. However, different applications may have different requirements for data accuracy. Instead of keeping multiple compressed versions of a time series w.r.t. different error bounds, HIRE hierarchically maintains a tree, where the root records a constant function to approximate the whole time series, and each other node records a constant function to approximate a part of the residual function of its parent for a particular time period. To retrieve data w.r.t. a specific error bound, it traverses the tree from the root down to certain levels according to the requested error bound and aggregates the constant functions on the visited nodes to generate a new bounded error compressed version dynamically. However, the number of nodes to be visited is unknown before the tree traversal completes, and thus the data size of the new version. In this paper, a time series is progressively decomposed into multiple piecewise linear functions. The first function is an approximation of the original time series w.r.t. the largest error bound. The second function is an approximation of the residual function between the original time series and the first function w.r.t. the second largest error bound, and so forth. The sum of the first, second, …, and m-th functions is an approximation of the original time series w.r.t. the m-th error bound. For each iteration, Swing-RR is used to generate a Bounded Error Piecewise Linear Approximation (BEPLA). Resolution Reduction (RR) plays an important role. Eight real-world datasets are used to evaluate the proposed method. For each dataset, approximations w.r.t. three typical error bounds, 5%, 1%, and 0.5%, are requested. Three BEPLAs are generated accordingly, which can be summed up to form three approximations w.r.t. the three error bounds. For all datasets, the total data size of the three BEPLAs is almost the same, with the size used to store just one version w.r.t. the smallest error bound and significantly smaller than the size used to keep three independent versions. The experiment result shows that the proposed method, referred to as PBEPLA-RR, can achieve very good compression ratios and provide multiple approximations w.r.t. different error bounds.

EXPLORING THE PREDICTIVE POTENTIAL OF EDUCATIONAL DATA MINING: A STUDY ON UNIVERSITY STUDENTS' ACADEMIC PERFORMANCE

Predicting student’s performance become more tough due to a huge volume of data in educational database. Even though data mining has been efficiently implemented in the business world. Use of data mining is relatively new in higher education, i.e., it used for recognition and extraction of potentially and advanced precious knowledge from huge amount of data using the concept of data mining. Model should be developed which can determine the conclusion from student’s academic success. In this study,the concept of educational data mining have been used. It is a computational process of discovering patterns in a large dataset and transform it into understandable structure for further use. Student data collected from different institutes. The scope of this research is to identify the factors influencing the performance of students in universities. To predict the performance of university student, for clustering purposes K mean algorithm and two algorithms of classification Decision tree (J48) and Naive Bays have been used,also compare the results of Decision tree J48 and Naive Bay’s algorithms which gives the better results according to their accuracy . For this purpose, weka tool was used to implement the algorithms. This study helps the educational institutions to identify such factors which affect the student performance and to eliminate these causes to enhance their performance.

Physically interpretable performance metrics for clustering.

Clustering is a type of machine learning technique, which is used to group huge amounts of data based on their similarity into separate groups or clusters. Clustering is a very important task that is nowadays used to analyze the huge and diverse amount of data coming out of molecular dynamics (MD) simulations. Typically, the data from the MD simulations in terms of their various frames in the trajectory are clustered into different groups and a representative element from each group is studied separately. Now, a very important question coming in this process is: what is the quality of the clusters that are obtained? There are several performance metrics that are available in the literature such as the silhouette index and the Davies-Bouldin Index that are often used to analyze the quality of clustering. However, most of these metrics focus on the overlap or the similarity of the clusters in the reduced dimension that is used for clustering and do not focus on the physically important properties or the parameters of the system. To address this issue, we have developed two physically interpretable scoring metrics that focus on the physical parameters of the system that we are analyzing. We have used and tested our algorithm on three different systems: (1) Ising model, (2) peptide folding and unfolding of WT HP35, (3) a protein-ligand trajectory of an enzyme and substrate, and (4) a protein-ligand dissociated trajectory. We show that the scoring metrics provide us clusters that match with our physical intuition about the systems.

Digitization of social welfare entities and its importance for the effective implementation of social services in the public management system

Background: For almost a decade, before the Covid-19 pandemic forcefully highlighted the importance of this area, the digital future of Europe had been the main focus of European Union politicians and senior officials. In February 2020, the European Commission published the communication “Shaping Europe’s Digital Future,” which outlines the European Union's digital transformation strategy. Research objectives: This article aims to identify the information and communication technology tools used by a public entity providing social services such as a Social Assistance Centre (SAC). The SAC is the basic organizational entity implementing social policy goals in the social welfare subsystem, functioning in every municipality in Poland. Research design and methods: The research method used in this article was a case study. Results: The implementation of digital tools into the OPS enabled the entity to identify problems in real time and respond to them faster, make more accurate decisions faster and more efficiently, and access a huge amount of data that improved the analyses carried out. Conclusions: The use of modern technologies in organizations providing social services contributes to a better use of available resources. In the broader perspective of city, regional, or national governance, the use of ICT provides new evidence for the design of community-based public policies and their adaptation to new realities, enables reforming the operation of public organizations, and increases the transparency of public sector activities.

An efficient optimized encryption and compression techniques to improve medical image security and transmission in the cloud

As digital technology for illness diagnosis and analysis has advanced, medical images are sent over the Internet. Cloud computing plays a major role for low-cost data storage and data sharing. In the healthcare industry, data security and privacy are key issues with cloud computing. It is imperative that healthcare professionals make sure that patient data is safe against hackers, unauthorized access, and thrift. To secure the confidential data and store the huge amount of data, encryption and compression techniques are used. This paper provides an enhanced optimized encryption and efficient hybrid compression strategies based on cloud environment. The proposed model involves various operations such as generate optimal key, encryption, compression, decompression and decryption. In order to transfer the data using high speed cloud data retrieval, we initially propose the Huffman Fano Hybrid Entropy approach. In the next step, the proposed model performs Elliptic Curve Coding based encryption technique to secure compressed medical image transmission. Here the shared secret keys are generated optimally by dynamic group based cooperative optimization algorithm, which makes use of the encryption quality measures and is called DGBCO–ECC model. On the receiving end, the image is decrypted and decompressed. The proposed model performance is validated by exploiting various parameters namely Mean Square Error, Standard Deviation of the Mean Error, Universal image quality index, Structural Similarity Index, Entropy, Peak Signal to Noise Ratio, Compression Ratio, Data Rate Saving and compression time. When the experimental outcome is contrasted with existing methods, it is found to perform better.

Investment Market Trend Forecasting and Strategy Optimization based on Big Data Analytics

The financial market is an important part of the global economy, and there exists a certain special internal regularity in its changes. With the rapid development of big data technology, the huge amount of data in the financial market provides new opportunities for the prediction of investment trends and strategy optimization. Based on big data analytics technology, combined with machine learning models, the study explores how to construct investment market trend prediction models through effective data preprocessing and feature engineering, and evaluates and compares the performance of different prediction models. How to accurately predict the direction of the financial market will be an important reference value for relevant practitioners as well as researchers. Traditional financial time series research mainly focuses on linear trend fitting based on statistical knowledge, however, the trend of the financial market is not limited to pure mathematical and rational function curves, the financial market is affected by a combination of various factors from all walks of life. Big data analytics has significant application potential in the investment market, providing investors with more scientific and accurate decision support.

Computer-Aided System for Customs Fraud Analytics Based on Artificial Intelligence Techniques

Globalization has stimulated the opening of the market and the accumulation of huge amounts of data, which consequently leads to an increase in the importance of the control of customs operations. However, customs data is highly imbalanced and this poses challenges in its integration and processing. Therefore, it is of prime importance to find automatic computationally intelligent solutions for customs management. The purpose of the research presented in this paper is to propose a computer-aided system for customs fraud analytics based on artificial intelligence techniques, ensuring the application and verification of methods and algorithms for integration, management, analysis and visualization of data on customs violations. The architecture of the customs violation data analysis system consists of the following components: data sources, data storage, data integration and preprocessing, real-time data flow, modeling, analysis and storage of analytical data, and visualization of the results. A machine learning approach for detecting customs fraud through unstructured data analysis is proposed. An artificial neural network designed for data analysis is designed, and the input data is divided into training data and testing data. A reduced set of statistical records related to the analysis of heterogeneous databases of different institutions, which is stored in a data warehouse, are used as experimental data. The first 80% of the data are used to train the neural network and the remaining 20% to test the trained network. Experimental results show that the calculated accuracy increases with increasing epochs and is higher for the training data and lower for the validation test data. Thus, the trained model can be saved and used to monitor for anomalies. The trained model is applied to the system to calculate new input parameters that were not used in either training or validation.

Enhanced Solar Power Prediction Using Attention-Based DiPLS-BiLSTM Model

The data for solar power generation contain a huge amount of data with a large number of features which are difficult to extract effectively. It is important for the grid management and operational efficiency of the solar farm to accurately predict the solar power. The existing prediction models utilize historical data but often fail to capture critical latent features. This limitation leads to overlooked complex dependencies or temporal relationships, reducing prediction accuracy, especially in load and generation forecasting. An attention-based dynamic inner partial least squares (DiPLS) model and a bidirectional long short-term memory (BiLSTM) model were used for solar power prediction. First, DiPLS is used to dynamically extract features, and then, an attention process is used to predict the importance of these features. Finally, the raw sets are input to the BiLSTM model to make predictions of solar power in the future. The proposed method improves prediction accuracy, achieving an R2 value of 0.965 for training and 0.961 for testing, compared to conventional models. Additionally, the method demonstrated lower root mean squared error (RMSE), indicating enhanced stability and accuracy for solar power forecasting.

Bi-modal contrastive learning for crop classification using Sentinel-2 and Planetscope

Remote sensing has enabled large-scale crop classification for understanding agricultural ecosystems and estimating production yields. In recent years, machine learning has become increasingly relevant for automated crop classification. However, the existing algorithms require a huge amount of annotated data. Self-supervised learning, which enables training on unlabeled data, has great potential to overcome the problem of annotation. Contrastive learning, a self-supervised approach based on instance discrimination, has shown promising results in the field of natural as well as remote sensing images. Crop data often consists of field parcels or sets of pixels from small spatial regions. Additionally, one needs to account for temporal patterns to correctly label crops. Hence, the standard approaches for landcover classification cannot be applied. In this work, we propose two contrastive self-supervised learning approaches to obtain a pre-trained model for crop classification without the need for labeled data. First, we adopt the uni-modal contrastive method (SCARF) and, second, we use a bi-modal approach based on Sentinel-2 and Planetscope data instead of standard transformations developed for natural images to accommodate the spectral characteristics of crop pixels. Evaluation in three regions of Germany and France shows that crop classification with the pre-trained multi-modal model is superior to the pre-trained uni-modal method as well as the supervised baseline models in the majority of test cases.

The new era of Technology Mysticism: Generative Artificial Intelligence and its effects

Generative Artificial Intelligence (GenAI) started to disrupt many application areas in the domain of information technology and is developing at a rapid pace. GenAI exhibits different systemic characteristics, it is a trained technology as opposed to the engineered technologies that have been developed in the IT domain in the past. As trained technologies are heavily depending on huge amounts of training data, their behaviour is not deterministic but of a stochastic nature, leading to a limited understanding of those systems. their behaviour is emergent. Assumptions and beliefs in the abilities of technologies by their users create a new age of mysticism that can be compared with our past and the relation of people in medieval times to the age of Mysticism with respect to their understanding of nature and their surroundings. We are facing AI today like our ancestors faced incomprehensible natural phenomena. This article is discussing the resulting effects from a technical but also from a philosophical perspective.

Graph regularized least squares regression for automated breast ultrasound imaging

Breast cancer, recognized as one of the most pervasive malignancies affecting females, manifests a perpetual escalation in its worldwide morbidity. Timely screening offers patients interventions that are not only more expeditious but also more efficacious. ABUS, as an automated breast ultrasound imaging technology, has the advantages of high resolution, reproducible results, and strong objectivity. However, manual interpretation of ABUS images can be highly tedious and laborious when handling huge amounts of data from images, may leading to the risk of missed diagnosis. In practical clinical diagnosis, the incorporation of Computer-Aided Diagnosis (CAD) systems emerges as a more favorable option. In consideration of the holistic factors encompassing model construction efficiency, training cost and overall performance, we provide a unique subspace clustering approach known as Graph regularized Least Squares Regression (GLSR) in this paper. Firstly, we encode the data's intrinsic geometry into the framework of least squares regression to respect local and global correlation structures at the same time. Secondly, we construct a nearest neighbor graph to model the smooth structure of the representation, which may lead to a more accurate representation. Finally, a nonnegative constraint is introduced into our framework so that the representation obtained by GLSR has clearer physical meaning. We provide an optimization approach for solving such a framework based on iterative updates of four blocks. Extensive experimental results indicate the effectiveness of the proposed method compared with state-of-the-art approaches on real-world breast cancer images and other biological data.

Machine Learning-Driven Stock Selection System: A Proposed Multi-Factor Model-Based Navigation Tool for the Chinese Financial Market

In view of the constantly changing and volatile nature of the Chinese financial landscape, characterized by the introduction of high-tech and huge amounts of market data, there is a need for an improved method for stock selection. Conventional stock methods are, however, inadequate due to their tendency to ignore the high volatility of the market and the nonlinear relationship between many financial variables which are at play. They have not been able to deliver predictions that are strong and accurate. This research, therefore, aims to explore how machine learning algorithms can be utilized to improve the accuracy and adaptability of stock selection models, thereby addressing these limitations. Through empirical results, it can be claimed that ML models, especially tree-based algorithms like LightGBM and XGBoost, are superior to traditional models in predicting stock returns. In this case, rolling windows are very well adapted to machine learning methods, which stand out as superior in terms of the adaptability to the changing stock market conditions. In addition, the research reveals the necessity of integrating the market-driven data, for instance, the trading volume and the momentum, into the stock selection models can help to better capture short-term pricing dynamics. The dissertation concludes with a machine learning-based stock selection system that is optimized for the Chinese financial market. The results of this work will increase the knowledge of quantitative finance by showing the machine learning algorithms can be more accurate in stock selection, and at the same time, providing practical solutions to the investors and financial institutions. The research emphasizes the necessity of combining modern computational methods and traditional financial theories to devise more effective and adaptive investment strategies in a complicated financial environment.

Using deep learning and word embeddings for predicting human agreeableness behavior

The latest advancements of deep learning have resulted in a new era of natural language processing. The machines now possess an unparallel ability to interpret and engage with various tasks such as text classification, content generation and natural language understanding. This development extended to the analysis of human behavior, where deep learning models are used to decode human personality. Due to the rise of social media, generating huge amounts of textual data that reshaped communication patterns. Understanding personality traits is a challenging topic which helps us to explore the patterns of thoughts, feelings and behaviors which are helpful for recruitment, career counselling and consumers’ behavior for marketing, etc. In this research study, the main aim is to predict the human personality trait of agreeableness showing whether a person is emotional who feels a lot or thinker who is logical and has rational thinking. This behavior leads to analyzing them as cooperative, friendly and respecting difference of views. For comprehensive empirical analysis, shallow machine learning models, ensemble models, and deep learning technique including state of the art transformer-based models are applied on real-world dataset of MBTI. For feature engineering, textual features of TF-IDF and POS tagging and word embeddings such as word2vec, glove and sentence embeddings are explored. The results analysis shows the highest performance 91.57% with sentence embeddings utilizing Bi-LSTM algorithm that highlights the power of this study as compared to existing studies in the relevant literature.

Methods and Results of the Study of the Phenomenon of Soviet Nostalgia in the Russian Media Space

The article is devoted to the phenomenon of digitalization of Soviet nostalgia. Special attention is paid to the nature of modern media discussions about the Soviet past, in which anti-communist sentiments are intertwined with nostalgia for the late Soviet period. The relevance of the study is connected with the increasing infl uence of a wide public audience in the era of digitalization on historical memory, previously formed mainly by professional historians and ideologists. The USSR is seen as a “place of memory” (according to Pierre Nora), which has a special symbolic signifi cance at the modern stage of development. The authors emphasize the changing balance between communicative and cultural memory in the era of digital technologies, as well as the need to develop new methods of analysis to work with huge amounts of data. The review of current studies of Soviet nostalgia in the media space allows us to identify the main vectors of development of Russian digital humanities, as well as analyze the reasons for the continued interest in nostalgic discussions in online communities, social networks and other media platforms. We make a conclusion that in modern scientifi c discourse there are two approaches to the study of the image of the USSR in the mass consciousness: fi rst, the analysis of the content of media content about “the Soviet” (very diverse in quality and form), and second, the study of user/viewer reaction (reception). There is an indication of tendencies in the Russian media space to depoliticize the discussion of the Soviet period. However, nostalgic debates continue to mark the boundaries of the confrontation between liberals-anti-Soviets, Soviet patriots and patriots-patriots, indicating the presence of several ideological splits in Russian society. Social networks become a platform for the formation of alter and counter narratives, contributing to the maintenance of pluralism of opinions and knowledge about the past. The study reveals three components of nostalgic discussions: comparison of the past and the present, ideological opposition, (and the least politicized) admiration for Soviet aesthetics and everyday life