Advances in Computational Intelligence and Robotics, pages 321-338

The Layout of Sentiment Lexica in Word Vector Space

Publication typeBook Chapter
Publication date2020-01-31
Quartile SCImago
Quartile WOS
Impact factor
ISSN23270411, 2327042X
Abstract

Sentiment lexicons play an important role in opinion mining systems and cognitive linguistics. Previous work aimed mostly at creating sentiment lexicons, but not thorough research into their fundamental properties. In this chapter, the arrangement of sentiment lexica in the multidimensional space of distributed word representations is studied. A hypothesis on the existence of sentiment lexica concentration areas is introduced, and it is tested on the basis of the joint analysis of the distribution of sentiment words and general lexica. The results of the test allow to confirm the proposed hypothesis for universal and domain-oriented sentiment lexicons. Also, the experiments discover the words which more than 80% of the sentiment lexica is concentrated around.

Metrics
Share
Cite this
GOST |
Cite this
GOST Copy
Razova E., Kotelnikov E. The Layout of Sentiment Lexica in Word Vector Space // Advances in Computational Intelligence and Robotics. 2020. pp. 321-338.
GOST all authors (up to 50) Copy
Razova E., Kotelnikov E. The Layout of Sentiment Lexica in Word Vector Space // Advances in Computational Intelligence and Robotics. 2020. pp. 321-338.
RIS |
Cite this
RIS Copy
TY - GENERIC
DO - 10.4018/978-1-7998-3038-2.ch015
UR - https://doi.org/10.4018%2F978-1-7998-3038-2.ch015
TI - The Layout of Sentiment Lexica in Word Vector Space
T2 - Advances in Computational Intelligence and Robotics
AU - Razova, Elena
AU - Kotelnikov, Evgeny
PY - 2020
DA - 2020/01/31 00:00:00
PB - IGI Global
SP - 321-338
SN - 2327-0411
SN - 2327-042X
ER -
BibTex
Cite this
BibTex Copy
@incollection{2020_Razova
author = {Elena Razova and Evgeny Kotelnikov},
title = {The Layout of Sentiment Lexica in Word Vector Space},
publisher = {IGI Global},
year = {2020},
pages = {321--338},
month = {jan}
}
Found error?