Author pages are created from data sourced from our academic publisher partnerships and public sources.
Share This Author
An Approach to Clustering Abstracts
The preliminary experiments show that abstracts cannot be clustered with the same quality as full texts, though the achieved quality is adequate for many applications; accordingly, Makagonov's proposal that digital libraries should provide document images of full texts of the papers (and not only abstracts) for open access via Internet, in order to help in search, classification, clustering, selection, and proper referencing of the books.
Clustering Abstracts Instead of Full Texts
One of the conclusions is the suggestion for the digital libraries and other repositories to provide document images of full texts of the papers along with their abstracts for open access via Internet.
Adverse Drug Extraction in Twitter Data Using Convolutional Neural Network
- L. Akhtyamova, M. Alexandrov, J. Cardiff
- Computer Science28th International Workshop on Database and…
- 14 March 2017
This research uses convolutional neural networks with word2vec embedding to classify user comments on Twitter to reveal adverse drug reactions of users, showing the overall usefulness of neural network algorithms in this kind of tasks.
Selection of Representative Documents for Clusters in a Document Collection
The algorithms are given, which rely on a dictionary of keywords reflecting the topic of the user’s interest, which select a document in each cluster basing on its closeness to the other ones.
Sense Cluster Based Categorization and Clustering of Abstracts
This paper focuses on the use of sense clusters for classification and clustering of very short texts such as conference abstracts, extracted from abstracts by exploiting the WordNet relationships existing between words in the same text.
Artificial intelligence driven solutions to business and engineering problems
The decision-making support system (DSS) SVIR and manual procedures of the Muchnik method are used to solve the problem of selection of perspective objects for investments and both approaches lead to close results.
Detecting Inflection Patterns in Natural Language by Minimization of Morphological Model
An unsupervised method of recognition of inflection patterns automatically, with no a priori information on the given language, basing exclusively on a list of words ex- tracted from a large text, shows promising results on different European languages.
Inductive Modeling in Subjectivity/Sentiment Analysis(case study: dialog processing)
Building Classifiers with GMDH for Health Social Networks (DB AskaPatient)
- L. Akhtyamova, M. Alexandrov, J. Cardiff, O. Koshulko
- Computer ScienceIEEE 13th International Scientific and Technical…
- 1 September 2018
Possibility of Group Method of Data Handling (GMDH) to classify data from health social networks for the analysis of the most interesting cases for users by using combined classes reflecting more practical view on medicines and treatments is studied.
Creating Collections of Descriptors of Events and Processes Based on Internet Queries
The experience in creating databases of descriptors (queries and their combinations) to be used in real problems is presented and an example related to the analysis and forecast of regional economy illustrates an application of the mentioned descriptors.