Supplementary Proceedings of the 5th International Conference on Analysis of Images, Social Networks and Texts (AIST-SUP 2016), Yekaterinburg, Russia, April 7-9, 2016.
AIST is a scientific conference on Analysis of Images, Social Networks, and Texts. The conference is intended for computer scientists and practitioners whose research interests involve Internet mathematics and other related fields of data science. Similar to the previous year, the conference will be focused on applications of data mining and machine learning techniques to various problem domains: image processing, analysis of social networks, and natural language processing. We hope that the participants will benefit from the interdisciplinary nature of the conference and exchange experience.
This paper discusses the design and development of software tools for simulation of social networks. It is well known that social networks have become the object of attention of sociologists, political scientists, market-ers, etc. The paper identifies two trends in the investigation of social networks: static and dynamic. Static approach involves the study of geometric forms of social networking, network structure (topology), its basic properties (the degree of centrality, distance, and so on). The dynamic approach makes it possible to follow the various stages of a social network formation, to identify the connec-tions between nodes of social network, to identify the formation of clusters in the Internet-graph. Paper considers the existing software tools for social net-work simulation and put forward demands to the software of this kind (agent-based approach, distributed simulation). Moreover paper discusses if it is possi-ble to use computer network simulator TriadNS for modeling of social networks and the definition of both static and dynamic characteristics of these networks.
We study topic models designed to be used for sentiment analysis, i.e., models that extract certain topics (aspects) from a corpus of documents and mine sentiment-related labels related to individual aspects. For both direct applications in sentiment analysis and other uses, it is desirable to have a good lexicon of sentiment words, preferably related to different aspects in the words. We have previously developed a modification for several popular sentiment-related LDA extensions that trains prior hyperparameters β for specific words. We continue this work and show how this approach leads to new aspect-specific lexicons of sentiment words based on a small set of “seed” sentiment words; the lexicons are useful by themselves and lead to improved sentiment classification.
The paper presents a free and open source toolkit which aim is to quickly deploy web services handling distributed vector models of semantics. It fills in the gap between training such models (many tools are already available for this) and dissemination of the results to general public. Our toolkit, WebVectors, provides all the necessary routines for organizing online access to querying trained models via modern web interface. We also describe two demo installations of the toolkit, featuring several efficient models for English, Russian and Norwegian.
Despite widespread scholarly attention on social movement media coverage, the full range of organizations appearing in the media with movements remains underexamined. To analyze this organizational complexity, we draw upon field theory, relating it to concepts from social network analysis. We hypothesize that interactions with stateembedded actors increase field stability, yet this effect decreases with the field's level of abstraction. We contrast a pair of US movements, the Tea Party and Occupy Wall Street, according to their interactions with stateembedded actors. Through the New York Times's API, we collect and produce article coappearance networks that approximate the population of Times’s indexed organizations. We parse fields from these networks using community detection algorithms. Our analyses test stability using triadic closure propensities and average coreness. Our findings show that subgroups affiliated with the Tea Party had greaterstability than those of Occupy Wall Street.
Helping behavior is a significant part of social learning process in online games. One type of such a behavior is answering questions in a chat. We provide a method to detect if the question asked in a chat was answered and by whom. Proposed method is based on topic modeling for chat messages and comparison of a detected topic of question with a topic of possible reply. We show its efficiency on chat messages from online games.
In this work, we compare two extensions of two different topic models for the same problem of recommending full-text items: previously developed SVD-LDA and its counterpart SVD-ARTM based on additive regularization. We show that ARTM naturally leads to the inference algorithm that has to be painstakingly developed for LDA.
The authors propose new formal foundations and design approach to develop an evolving semantic platform for finding experts relevant to events arising in the open environment of modern economical clusters. This work offers a new implementation of probabilistic latent topic modeling method with two linked indicators (categories and experts) to mach expertise. In order to show feasibility of the solution a distributed and service-oriented software prototype of the web-based semantic platform was developed. Solution provides results with high precision scores and evolves in accordance with changes over time. Fusing together ontology-aided expertise matching and service-oriented software design suitable for developing evolvable semantic applications our approach facilitates effective and efficient knowledge exchange. That prototype called EXPERTIZE was evaluated for a particular case of experts finding in the university clusters.