KFU. Card publication. Exploring convolutional neural networks and topic models for user profiling from drug reviews

KAZAN
FEDERAL UNIVERSITY

- RUS
- 中文
- ES

EXPLORING CONVOLUTIONAL NEURAL NETWORKS AND TOPIC MODELS FOR USER PROFILING FROM DRUG REVIEWS

Form of presentation

Articles in international journals and collections

Year of publication

2017

��

��

Authors, employees of KFU

Nikolenko Sergey Igorevich, author

Tutubalina Elena Viktorovna, author

Bibliographic description in the original language

Tutubalina Elena, Nikolenko Sergey. Exploring convolutional neural networks and topic models for user profiling from drug reviews // Multimedia Tools and Applications. — 2017.

Annotation

Pharmacovigilance, and generally applications of natural language processing models to healthcare, have attracted growing attention over the recent years. In particular, drug reactions can be extracted from user reviews posted on the Web, and automated processing of this information represents a novel and exciting approach to personalized medicine and wide-scale drug tests. In medical applications, demographic information regarding the authors of these reviews such as age and gender is of primary importance; however, existing studies usually either assume that this information is available or overlook the issue entirely. In this work, we propose and compare several approaches to automated mining of demographic information from user-generated texts. We compare modern natural language processing techniques, including extensions of topic models and convolutional neural networks (CNN). We apply single-task and multi-task learning approaches to this problem.

Keywords

text mining, natural language processing, topic modeling, deep learning, convolutional neural networks, multi-task learning, single-task learning, user reviews, demographic prediction, demographic attributes, social media, mental health

The name of the journal

Multimedia Tools and Applications

URL

http://rdcu.be/yexM

Please use this ID to quote from or refer to the card

https://repository.kpfu.ru/eng/?p_id=167066&p_lang=2

Resource files

File name	Size (MB)	Format
exploring_convolutional_neural_4.pdf	0,91	pdf	show / download

Full metadata record

Field DC	Value	Language
dc.contributor.author	Nikolenko Sergey Igorevich	ru_RU
dc.contributor.author	Tutubalina Elena Viktorovna	ru_RU
dc.date.accessioned	2017-01-01T00:00:00Z	ru_RU
dc.date.available	2017-01-01T00:00:00Z	ru_RU
dc.date.issued	2017	ru_RU
dc.identifier.citation	Tutubalina Elena, Nikolenko Sergey. Exploring convolutional neural networks and topic models for user profiling from drug reviews // Multimedia Tools and Applications. — 2017.	ru_RU
dc.identifier.uri	https://repository.kpfu.ru/eng/?p_id=167066&p_lang=2	ru_RU
dc.description.abstract	Multimedia Tools and Applications	ru_RU
dc.description.abstract	Pharmacovigilance, and generally applications of natural language processing models to healthcare, have attracted growing attention over the recent years. In particular, drug reactions can be extracted from user reviews posted on the Web, and automated processing of this information represents a novel and exciting approach to personalized medicine and wide-scale drug tests. In medical applications, demographic information regarding the authors of these reviews such as age and gender is of primary importance; however, existing studies usually either assume that this information is available or overlook the issue entirely. In this work, we propose and compare several approaches to automated mining of demographic information from user-generated texts. We compare modern natural language processing techniques, including extensions of topic models and convolutional neural networks (CNN). We apply single-task and multi-task learning approaches to this problem.	ru_RU
dc.language.iso	ru	ru_RU
dc.subject	text mining	ru_RU
dc.subject	natural language processing	ru_RU
dc.subject	topic modeling	ru_RU
dc.subject	deep learning	ru_RU
dc.subject	convolutional neural networks	ru_RU
dc.subject	multi-task learning	ru_RU
dc.subject	single-task learning	ru_RU
dc.subject	user reviews	ru_RU
dc.subject	demographic prediction	ru_RU
dc.subject	demographic attributes	ru_RU
dc.subject	social media	ru_RU
dc.subject	mental health	ru_RU
dc.title	Exploring convolutional neural networks and topic models for user profiling from drug reviews	ru_RU
dc.type	Articles in international journals and collections	ru_RU