This volume contains the refereed proceedings of the 7th International Conference on Analysis of Images, Social Networks, and Texts (AIST 2018)1. The previous conferences during 2012{2017 attracted a signi cant number of data scientists { students, researchers, academics, and engineers working on interdisciplinary data analysis of images, texts, and social networks. The broad scope of AIST made it an event where researchers from di erent domains, such as image and text processing, exploiting various data analysis techniques, can meet and exchange ideas. We strongly believe that this may lead to cross-fertilisation of ideas between researchers relying on modern data analysis machinery. Therefore, AIST brought together all kinds of applications of data mining and machine learning techniques. The conference allowed specialists from di erent elds to meet each other, present their work, and discuss both theoretical and practical aspects of their data analysis problems. Another important aim of the conference was to stimulate scientists and people from industry to bene t from the knowledge exchange and identify possible grounds for fruitful collaboration. The conference was held during July 5{7, 2018. The conference was organized in Moscow, the capital of Russia, on the campus of Moscow Polytechnic University (MPU)2. This year, the key topics of AIST were grouped into six tracks: The Programme Committee and the reviewers of the conference included 154 well-known experts in data mining and machine learning, natural language pro-
cessing, image processing, social network analysis, and related areas from leading institutions of 32 countries including Argentina, Australia, Austria, Bangladesh, Canada, China, Croatia, Czech Republic, Denmark, Egypt, Finland, France, Germany, Greece, India, Italy, Kazakhstan, Lithuania, Norway, Qatar, Romania, Russia, Slovenia, Spain, Switzerland, Vietnam, Taiwan, Turkey, Ukraine, The Netherlands, UK, and USA. This year we received 107 submissions mostly from Russia but also from Austria, Bangladesh, Finland, Germany, , Norway, Switzerland, Taiwan, Turkey, Ukraine, USA, and Vietnam.
Out of 107 submissions, only 29 papers were accepted as regular oral papers. Thus, the acceptance rate of this volume was around 36% (not taking into account 26 automatically rejected papers). In order to encourage young practitioners and researchers, we included 28 papers to the supplementary proceedings after their poster presentation at the conference. Each submission was reviewed by at least three reviewers, experts in their elds, in order to supply detailed and helpful comments.
The conference featured several invited talks and an industry session dedicated to current trends and challenges.
The topical opening talk was presented by Rostislav Yavorskiy on \Visualization of Data Science Community in Russia."
The invited talks were: { Anne Rozinat (Fluxicon), \Process Mining: Discovering Process Maps from Data";
{ Goran Glavas (University of Mannheim), \Cars, Drivers, Vehicles, and Wheels: Specializing Distributional Word Vectors for Lexico-Semantic Relations"; { Gleb Gusev (Yandex and Moscow Institute of Physics and Technology), \Machine Learning Research in Yandex and CatBoost";
{ Ekaterina Chernyak of HSE and Sberbank presented a tutorial on \Supervised Methods in Natural Language Processing."
The business speakers also covered a wide variety of topics. We list those invited talks below: { Iosif Itkin (Exactpro Systems), \The World's Most Valuable Commodity"; { Maksim Balashevich (Santiment), \Crypto assets valuation"; { Ilya Utekhin (the European University at St. Petersburg), \On understanding users for human-centered design";
{ Denis Stepanov (JetBrains), \Workshop: Data visualization with datalore.plot in research, education and just for fun"; { Eugeny Malyutin (OK.ru), \Trend detection at OK"; { Oleg Klepikov (Center for Applied Neuroeconomics), \Psychometric behavorial classi cation of banking clients { a case study";
{ Dmitriy Skougarevskiy (the European University at St. Petersburg), \Semantic representation of accident reports to understand the dark gure of crime."
Under a special agreement between the responsible program co-chairs and the proceedings chair, due to its interdisciplinary nature, one paperwas set to a special section on Innovative Systems (outside of the main tracks).
vi
We would like to thank the authors for submitting their papers and the members of the Programme Committee for their e orts in providing exhaustive reviews.
According to the Program Chairs taking into account the obtained reviews and presentation quality, the best paper awards were granted to the following papers:
Track 1. General topics of data analysis: \Lookup Lateration: Mapping of Received Signal Strength to Position for Geo-Localization in Outdoor Urban Areas" by Andrey Shestakov, Attila Kertesz-Farkas, Dmitri Shmelkin and Danila Doroshin;
Track 2. Natural language processing: \Learning representations for soft skill matching" by Luiza Sayfullina, Eric Malmi and Juho Kannala;
Track 3. Social network analysis: \Organizational networks revisited: Predictors of headquarters-subsidiary relationship perception" by Antonina Milekhina, Valentina Kuskova and Elena Artyukhova;
Track 4. Analysis of Images and Video: \Application of Fully Convolutional Neural Networks to Mapping Industrial Oil Palm Plantations" by Artem Baklanov, Mikhail Khachay and Maxim Pasynkov;
Track 5. Optimization problems on graphsand network structures: \E cient PTAS for the Euclidean CVRP with Time Windows" by Michael Khachay and Yuri Ogorodnikov;
Track 6. Analysis of dynamic behavior through event data: \Neural Approach to the Discovery Problem in Process Mining" by Timofey Shunin, Natalia Zubkova and Sergey Shershakov.
We would also like to express our special gratitude to all the invited speakers and industry representatives.
We deeply thank all the partners and sponsors. Our golden sponsors is Exactpro.
Exactpro, a fully owned subsidiary of the London Stock Exchange Group, specializes in quality assurance for exchanges, investment banks, brokers, and other nancial sector organizations. Our special thanks go to Springer for their help, starting from the rst conference call to the nal version of the proceedings. JetBrains covered important conference expenses while Springer sponsored the best paper awards. Last but not least, we are grateful to the dean of Information Technologies Faculty of MPU, Andrey Phillipovich, and all the organizers, especially to Andrey Novikov and Marina Danshina, and the volunteers, whose endless energy saved us at the most critical stages of the conference preparation.
Here, we would like to mention the Russian word \aist" is more than just a simple abbreviation (in Cyrillic) { it means a \stork." Since it is a wonderful free bird, a symbol of happiness and peace, this stork gave us the inspiration to organize the AIST conference. So we believe that this young and rapidly growing conference will likewise be bringing inspiration to data scientists around the world! October 2018
Wil van der Aalst Vladimir Batagelj
Goran Glavas
Dmitry Ignatov Michael Khachay Olessia Koltsova Sergei Kuznetsov
Irina Lomazova Natalia Loukachevitch
Amedeo Napoli Alexander Panchenko
Panos Pardalos
Marcello Pelillo
Andrey Savchenko
Organisation
Wil van der Aalst Vladimir Batagelj Goran Glavas Michael Khachay Sergei Kuznetsov Olessia Koltsova Amedeo Napoli Irina Lomazova Natalia Loukachevitch Alexander Panchenko Panos Pardalos Marcello Pelillo Andrey Savchenko
RWTH Aachen University, Germany University of Ljubljana, Ljubljana, Slovenia University of Mannheim, Mannheim, Germany Krasovskii Institute of Mathematics and Mechanics of Russian Academy of Sciences, Russia & Ural Federal University, Yekaterinburg, Russia National Research University Higher School of Economics, Moscow, Russia National Research University Higher School of Economics, St. Petersburg, Russia LORIA CNRS, University of Lorraine, and INRIA, Nancy, France National Research University Higher School of Economics, Moscow, Russia Computing Centre of Lomonosov Moscow State University, Russia University of Hamburg, Germany & Universite catholique de Louvain, Belgium University of Florida, US University of Venice, Italy National Research University Higher School of Economics, Nizhny Novgorod, Russia
Dmitry I. Ignatov
Rostislav Yavorskiy
National Research University Higher School of Economics, Russia
National Research University Higher School of Economics, Moscow
National Research University Higher School of Economics, Russia Krasovskii Institute of Mathematics and Mechanics of Russian Academy of Sciences, Russia & Ural Federal University, Yekaterinburg, Russia University of Hamburg, Germany & Universite catholique de Louvain, Belgium National Research University Higher School of Economics, Russia
Ekaterina Arkhangelskaya Aleksey Artamonov Xiang Bai Jaume Baixeries Amir Bakarov Artem Baklanov Lamberto Ballan Vladimir Batagelj Timo Baumann Malay Bhattacharyya Chris Biemann Battista Biggio Elena Bolshakova Samuel Bulo Andrea Burattin Evgeny Burnaev Aleksey Buzmakov Ignacio Cassol Artem Chernodub Mikhail Chernoskutov
St. Petersburg Department of Steklov Institute of Mathematics of Russian Academy of Sciences, Russia Neuromation, US Huazhong University of Science and Technology, China Universitat Politecnica de Catalunya, Spain National Research University Higher School of Economics, Russia International Institute for Applied Systems Analysis, Austria University of Padova, Italy Institute of Mathematics, Physics and Mechanics, Slovenia University of Hamburg, Germany Indian Statistical Institute, Kolkata University of Hamburg, Germany University of Cagliari, Italy Lomonosov Moscow State University, Russia Fondazione Bruno Kessler, Italy Technical University of Denmark, Denmark Skolkovo Institute of Science and Technology, Russia National Research University Higher School of Economics, Perm, Russia Universidad Austral, Argentina Institute of Mathematical Machines and Systems Problems of National Academy of Sciences of Ukraine, Ukraine Krasovskii Institute of Mathematics and Mechanics of the Ural Branch of the Russian Academy of Sciences and Ural Federal University, Russia Bonaventura Coppola Hernani Costa Massimiliano de Leoni Boris Dobrov So a Dokuka Dirk Fahland Stefano Faralli Victor Fedoseev Elena Filatova Olga Gerasimova Edward Kh. Gimadi Goran Glavas Ivan Gostev Natalia Grabar Artem Grachev Dmitry Granovsky Anna Gromova Marianne Huchard Dmitry Ignatov Dmitry Ilvovsky Vladimir Ivanov Pei Jun Alex Jung Anna Kalenkova Ilia Karpov Nikolay Karpov Egor Kashkin Alexander Kelmanov Attila Kertesz-Farkas
University of Trento, Italy University of Malaga, Spain Eindhoven University of Technology, the Netherlands Recearch Computing Center of Lomonosov Moscow State University, Russia National Research University Higher School of Economics, Russia Eindhoven University of Technology, the Netherlands University of Mannheim, Germany Samara National Research University, Russia City University of New York, US National Research University Higher School of Economics, Russia Sobolev Institute of Mathematics of the Siberian Branch of the Russian Academy of Sciences, Russia University of Mannheim, Germany National Research University Higher School of Economics, Russia STL CNRS Universite Lille 3, France Samsung R&D, Russia Yandex, Russia Exactpro, Russia LIRMM, Universite Montpellier 2 et CNRS, France National Research University Higher School of Economics, Russia National Research University Higher School of Economics, Russia Innopolis University, Russia Hefei University of Technology, China Aalto University, Finland National Research University Higher School of Economics, Russia National Research University Higher School of Economics, Russia National Research University Higher School of Economics, Nizhniy Novgorod, Russia Vinogradov Russian Language Institute of Russian Academy of Sciences, Russia Sobolev Institute of Mathematics of Siberian Branch of Russian Academy of Sciences, Russia National Research University Higher School of Economics, Russia Oleg Khamisov Vladimir Khandeev Alexander Kharlamov Javad Khodadoust Konstantin Kobylkin Yury Kochetov Sergei Koltcov Olessia Koltsova Jan Konecny Andrey Kopylov Mikhail Korobov Evgeny Kotelnikov Ilias Kotsireas Fedor Krasnov Olga Krasotkina Ekaterina Krekhovets Tomas Krilavicius Rauf Kurbanov Andrey Kutuzov Andrey Kuznetsov Sergei Kuznetsov Florence Le Ber Alexander Lepskiy Benjamin Lind Ma Lizhuang Nikola Ljubesic
Krasovskii Institute of Mathematics and Mechanics, Ural Branch of Russian Academy of Sciences and Ural Federal University, Russia Sobolev Institute of Mathematics, Siberian Branch of Russian Academy of Sciences, Russia Melentiev Energy Systems Institute, Siberian Branch of the Russian Academy of Sciences, Russia Sobolev Institute of Mathematics, Siberian Branch of Russian Academy of Sciences, Russia National Research University Higher School of Economics, Russia National Research University Higher School of Economics, Russia Krasovskii Institute of Mathematics and Mechanics, Ural Branch of Russian Academy of Sciences, Russia Sobolev Institute of Mathematics, Siberian Branch of Russian Academy of Sciences, Russia National Research University Higher School of Economics, Russia National Research University Higher School of Economics, Russia Palacky University, Czech Republic Tula State University, Russia ScrapingHub Inc., Ireland Vyatka State University, Russia Wilfrid Laurier University and Maplesoft, Canada Gazprom Neft, Russia Markov Processes International, US National Research University Higher School of Economics, Russia Vytautas Magnus University, Lithuania Neuromation, US University of Oslo, Norway Samara National Research University, Russia National Research University Higher School of Economics, Russia ICube Laboratory and Ecole Nationale du Genie de l'Eau et de l'Environnement de Strasbourg, France National Research University Higher School of Economics, Russia Anglo-American School of St. Petersburg, Russia Shanghai Jiao Tong University, China Jozef Stefan Institute, Slovenia and University of Zagreb, Croatia Alexey Malafeev Yury Malkov Eric Malmi Luis Marujo Eyasu Zemene Mequanint Nizar Messai Tristan Miller Olga Mitrofanova Evgeny Myasnikov Federico Nanni Amedeo Napoli Kirill Nikolaev Damien Nouvel Evgeniy M. Ozhegov Alina Ozhegova Anna Panasenko Alexander Panchenko Panos Pardalos Marcello Pelillo Georgios Petasis Stefan Pickl Lidia Pivovarova Vladimir Pleshko Alexander Porshnev Surya Prasath Andrea Prati Artem Pyatkin Evgeniy Riabenko Martin Riedl Alexey Romanov Yuliya Rubtsova
National Research University Higher School of Economics, Russia Lomonosov Moscow State University, Russia National Research University Higher School of Economics, Russia National Research University Higher School of Economics, Russia Institute of Applied Physics of the Russian Academy of Sciences, Russia Google, Switzerland Snap Research and Carnegie Mellon University, US Ca'Focasri University of Venice, Italy LI - Universite Francois Rabelais, France Technische Universitat Darmstadt, Germany St. Petersburg State University, Russia Samara National Research University, Russia University of Mannheim, Germany Universite de Lorraine, Nancy, France National Research University Higher School of Economics, Russia Institut National des Langues et Civilisations Orientales, France Higher School of Econommics National Research University Higher School of Economics Novosibirsk State University, Russia University of Hamburg, Germany University of Florida, US University of Venice, Italy National Centre for Scienti c Research \Demokritos" Universitat der Bundeswehr Munchen University of Helsinki, Finland RCO LLC, Russia National Research University Higher School of Economics, Nizhniy Novgorod, Russia Cincinnati Children's Hospital Medical Center, US University of Parma, Italy Novosibirsk State University and Sobolev Institute of Mathematics, Siberian Branch of Russian Academy of Sciences, Russia Facebook, UK University of Stuttgart, Germany University of Massachusetts Lowell, US Ershov Institute of Informatics Systems, Siberian Branch of Russian Academy of Sciences, Russia Alexey Ruchay Chelyabinsk State University, Russia Eugen Ruppert University of Hamburg, Germany Christian Sacarea Babes-Bolyai University, Romania Mohammed Abdel-Mgeed German University in Cairo, Egypt M. Salem Andrey Savchenko
Mikhail Batsyn Marc Chaumont Ivan Grechikhin Arsenis Tsokas Alexander Rassadin Yuri Rykov
Francois Suro Friedhelm Schwenker Oleg Seredin Andrey Shcherbakov Henry Soldano Alexey Sorokin Tobias Staron Dmitry Stepanov Vadim Strijov Diana Sungatullina Yonatan Tariku Irina Temnikova Rocco Tripodi Diana Troanca Christos Tryfonopoulos Elena Tutubalina Dmitry Ustalov Wil van der Aalst Sebastiano Vascon Natalia Vassilieva Dmitry Vetrov Ekaterina Vylomova Gui-Song Xia Roman Yangarber Marcos Zampieri Alexey Zobnin Nikolai Zolotykh National Research University Higher School of Economics, Nizhniy Novgorod, Russia Ulm University, Germany Tula State University, Russia University of Melbourne, Australia Universite Paris-Nord, France Lomonosov Moscow State University, Russia University of Hamburg, Germany Ailamazyan Program Systems Institute of Russian Academy of Sciences, Russia Dorodnicyn Computing Centre of Russian Academy of Sciences, Russia Skolkovo Institute of Science and Technology, Russia University of Central Florida, US Qatar Computing Research Institute, Qatar University of Venice, Italy Babes-Bolyai University, Romania University of Peloponnese, Greece Kazan Federal University, Russia University of Mannheim, Germany RWTH Aachen University, Germnay University Ca' Foscari of Venice, Italy Hewlett Packard Labs, Russia Lomonosov Moscow State University and National Research University Higher School of Economics, Russia University of Melbourne, Australia Wuhan University, China University of Helsinki, Finland University of Wolverhampton, UK National Research University Higher School of Economics, Russia University of Nizhniy Novgorod, Russia
Rostislav Yavorskiy, Conference Chair National Research University Higher School of Economics, Russia Andrey Novikov, Head of Organization National Research University Higher School of Economics, Russia Moscow Polytechnic University, Russia Marina Danshina, Venue Organization & Management Anna Ukhanaeva, Information Partners National Research University Higher and Communications School of Economics, Russia Anna Kalenkova, Visa Support and National Research University Higher International Communications School of Economics, Russia Alexander Gnevshev, Venue Moscow Polytechnic University, Russia Organization & Management
Daniil Bannyh Ksenia Belkova Tatiana Mishina Zahar Kuhtenkov Maxim Pasynkov Ivan Poylov
Golden sponsor: Bronze sponsors:
Moscow Polytechnic University, Russia Moscow Polytechnic University, Russia Moscow Polytechnic University, Russia Moscow Polytechnic University, Russia Krasovsky Institute of Mathematics and Mechanics of RAS, Russia, Yekaterinburg
Moscow Polytechnic University, Russia Exactpro JetBrains
Springer Characterizing Text Complexity with Core Vocabulary Distributional Patterns: Corpus-based Approach : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 110
Marina Solnyshkina, Vladimir Ivanov and Valery Solovyev Comparative Analysis of Classi cation Methods for Human Identi cation by gait : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 118
Lubov Shiripova and Evgeny Myasnikov Voronoi-based Path Planning based on Visibility and Kill/death Ratio Tactical Component : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 129
Ilya Makarov, Pavel Polyakov and Roman Karpichev Security System Event Log Analysis : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 141
Dmitry Chalyy, Nikolai Ovchenkov, Ekaterina Lazareva and Rafael Yaikov Evaluation of Nonlinear Dimensionality Reduction Techniques for Classi cation of Hyperspectral Images : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 147
Evgeny Myasnikov Fourty Years of Network Science: Analysis of Journal Contribution to the Field : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 155
Marina Kalinina, Vladimir Kuznetsov and Valentina Kuskova Image and Video Tag Aggregation : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 161
Olga Kanishcheva and Natalia Sharonova Text Scene Detection with Transfer Learning in Price Detection Task : : : : 173
Vladimir Fomenko, Dmitry Botov and Julius Klenin Veri cation of the Formal Approach to Data Fusion : : : : : : : : : : : : : : : : : : : 179
Ildar Baimuratov, Stefan Morozov and Nataly Zhukova Sentiment Analysis of Short Texts from Social Networks Using Sentiment Dictionaries and Blending of Machine Learning Algorithms : : : 190
Anastasia Novikova and Sergey Stupnikov Probability Analysis of the Vocabulary Size Dynamics Using Google Books Ngram Corpus : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 202
Yulia Maslennikova, Anastasia Pekina and Vladimir Bochkarev Neural Networks with Attention for Word Sense Induction : : : : : : : : : : : : : 208
Oleg Struyanskiy and Nikolay Arefyev Combined Machine-Learning Approach to PoS-Tagging of Middle English and Old Norse Texts : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 214
Raoul Karimov, Andrei Akinin and Dmytro Yakymets Text Normalization and Spelling Correction In Kazakh Language : : : : : : : 221
Gaukhar Slamova and Meruyert Mukhanova Static Gestures Classi cation Using Convolutional Neural Networks on the Example of the Russian Sign Language : : : : : : : : : : : : : : : : : : : : : : : : : : : 229 Oleg Potkin and Andrey Philippovich