Skip to main navigation
Skip to search
Skip to main content
The University of Brighton Home
Home
Profiles
Research units
Equipment
Projects
Research output
Activities
Student theses
Search by expertise, name or affiliation
Comparison of sentiment lexicons in localized English tweets
Bayode Ogunleye
School of Arch, Tech and Eng
Research output
:
Contribution to conference
›
Abstract
›
peer-review
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'Comparison of sentiment lexicons in localized English tweets'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Lexicon
100%
Tweets
100%
Pidgin English
100%
Sentiment Lexicon
100%
Sentiment Analysis
75%
Nigeria
50%
Bank Customers
50%
Sentiment Classification
50%
AFINN
50%
Retail
25%
Popular
25%
Beginner
25%
Airlines
25%
Products or Services
25%
Hospitality
25%
Time Waste
25%
Resource Waste
25%
Brand Image
25%
Social Media
25%
Business Value
25%
Social Media Users
25%
Spoken Language
25%
Twitter Data
25%
F1 Score
25%
Sarcasm
25%
Service Experience
25%
Maximize Profit
25%
Official Language
25%
Stock Market
25%
Background Knowledge
25%
Rights-based Approach
25%
Precision-recall
25%
Standard English
25%
Nigeria Banks
25%
Lexicon-based Approach
25%
Python Programming Language
25%
Natural Language Ambiguity
25%
Precision Score
25%
Big Social Data
25%
Sentiment Analytics
25%
Recall Score
25%
R Language
25%
Live-tweeting
25%
Image Monitors
25%
Arts and Humanities
Sentiment
100%
English
100%
Pidgin English
66%
Nigeria
50%
Opinion Mining
50%
Technique
33%
Programming Language
33%
Popular
16%
Crisis
16%
intentions
16%
beginners
16%
Retail
16%
Spoken Language
16%
Official Language
16%
Standard English
16%
Sarcasm
16%
Background Knowledge
16%
Computer Science
Sentiment Analysis
100%
Programming Language
66%
Sentiment Classification
66%
Analysis Technique
33%
Business Value
33%
Spoken Language
33%
Social Medium User
33%
Official Language
33%
Background Knowledge
33%
Lexicon-Based Approach
33%
Developing Area
33%
Social Sciences
English
100%
Creoles
57%
Nigeria
42%
Opinion Mining
42%
Programming Language
28%
Airline
14%
Brand Image
14%
Transport
14%
Educational Background
14%
Spoken Language
14%
Stock Market
14%
Regional Disparities
14%
Official Language
14%
Social Data
14%
Economics, Econometrics and Finance
Industry
100%
Brand Image
100%
Airline
100%
Engineering
Opinion Mining
100%