Analysis of Images, Social Networks and Texts 8th International Conference, AIST 2019, Kazan, Russia, July 17–19, 2019, Revised Selected Papers

This book constitutes the post-conference proceedings of the 8th International Conference on Analysis of Images, Social Networks and Texts, AIST 2019, held in Kazan, Russia, in July 2019.

The 27 full and 8 short papers were carefully reviewed and selected from 134 submissions (of which 21 papers were automatically rejected without being reviewed). The papers are organized in topical sections on general topics of data analysis; natural language processing; social network analysis; analysis of images and video; optimization problems on graphs and network structures; and analysis of dynamic behavior through event data.

Invited Opinion Talk.- Double-blind peer-reviewing and inclusiveness in Russian NLP conferences.- Tutorial.- Intel® Distribution of OpenVINO™ toolkit: a case study of semantic Segmentation.- General Topics of Data Analysis.- Experimental Analysis of Approaches to Multidimensional Conditional Density Estimation.- Histogram-based algorithm for building gradient boosting ensembles of piecewise linear decision trees.- Deep Reinforcement Learning in Match-3 Game.- Distance in Geographic and Characteristics Space for Real Estate Price Prediction.- Fast Nearest-Neighbor Classifier based on Sequential Analysis of Principal Components.- A Simple Method to Evaluate Support Size and Non-uniformity of a Decoder-Based Generative Model.- Natural Language Processing.- Biomedical Entities Impact on Rating Prediction for Psychiatric Drugs.- Combining Neural Language Models for WordSense Induction.- Log-based Reading Speed Prediction: a Case Study on War and Peace.- Cross-lingual argumentation mining for Russian texts.- Dynamic Topic Models for Retrospective Event Detection: A Study on Soviet Opposition-Leaning Media.- Deep Embeddings for Brand Detection in Product Titles.- Wear the Right Head: Comparing Strategies for Encoding Sentences for Aspects Extraction.- Combined Advertising Sign Classifier.- A comparison of algorithms for detection of "figurativeness" in metaphor, irony and puns.- Authorship Attribution in Russian with New High-Performing and Fully Interpretable Morpho-Syntactic Features.- Evaluation of Sentence Embedding Models for Natural Language Understating Problems in Russian.- Noun Compositionality Detection using Distributional Semantics for the Russian Language.- Deep JEDi: Deep Joint Entity Disambiguation to Wikipedia for Russian.- Selecting an optimal feature set for stance detection.- Social network analysis.- Analysis of Students Educational Interests Using Social Networks Data.- Multilevel Exponential Random Graph Models Application to Civil Participation Studies.- The Entity Name Identification in Classification Algorithm: Testing the Advocacy Coalition Framework by Document Analysis (the Case of Russian Civil Society Policy).- Analysis of Images and Video.- Multi-label Image Set Recognition in Visually-Aware Recommender Systems.- Input simplifying as an approach for improving neural network efficiency.- American and Russian Sign Language Dactyl Recognition and Text2Sign Translation.- Data augmentation with GAN: improving chest X-rays pathologies prediction on class-imbalanced cases.- Estimation of non-radial geometric distortions for dash cams.- On Expert-defined versus Learned Hierarchies for Image Classification.- A switching morphological algorithm for depth map recovery.- Learning to Approximate Directional Fields Defined over 2D Planes.- Optimization Problems on Graphs and Network Structures.- Fast and Exact Algorithms for Some NP-Hard 2-Clustering Problems in the One-Dimensional Case.-Efficient PTAS for the Euclidean Capacitated Vehicle Routing Problem with non-uniform non-splittable demand.- Analysis of Dynamic Behavior Through Event Data.- Detection of Anomalies in the Criminal Proceedings Based on the Analysis of Event Logs.- Method to Improve Workow Net Decomposition for Process Model Repair.