Detection of Offensive Tweets: A Comparative Study
Journal Title: Computer Reviews Journal - Year 2018, Vol 1, Issue 1
Abstract
With the growing popularity, Twitter has become a major platform for posting views via tweets. Tweets contain useful, relevant and offensive content as well. More than a decade of research has resulted in numerous techniques and models to detect offensive content. However, little is known about lexically offensive and contextual offensive content. In this research paper, lexical offensive contents have been identified using two techniques- Rule-Based Naive Bayes (RNB) and a collaborative model of LDA with Naïve Bayes (LDANB). LDANB provides better results as compared to RNB for lexical offensive tweet detection. Further, contextually offensive contents are detected using newly devised Adjective Based approach. Contextual offensive content results prove to be better with Adjective based approach than Cosine similarity based results. To validate results of applied offensive tweet detection techniques three performance metrics- precision, Accuracy and recall are used.
Authors and Affiliations
Niyati Aggrawal
Keywords
Related Articles
- EP ID EP433742
- DOI -
- Views 136
- Downloads 0
RLS Wiener Filter and Fixed-Point Smoother with Randomly Delayed or Uncertain Observations in Linear Discrete-Time Stochastic Systems
This paper designs the recursive least-squares (RLS) Wiener fixed-point smoother and filter from randomly delayed observed values by multiple sampling times or uncertain observations in linear discrete-time stochastic sy...
Review of Routing Protocol in a Wireless Sensor Network for an IOT Application
IoT (Internet of Things) create network of physical objects. Maximize network lifetime and optimizing the usage of network is the major objective. Survey is made on Delay, Energy, Jitter, Throughput, Packet Delivery Rati...
The MOUSE approach: Mapping Ontologies using UML for System Engineers
To address the problem of semantic heterogeneity, there has been a large body of research directed toward the study of semantic mapping technologies. Although various semantic mapping technologies have been investigated,...
On the Derivation and Analysis of a Highly Efficient Method for the Approximation of Quadratic Riccati Equations
A highly e¢cient method is derived and analyzed in this paper for the approximation of Quadratic Riccati Equations (QREs) using interpolation and collocation procedure. The derivation is carried out within a two-step int...
Cloud Computing and Cloud Automata as A New Paradigm for Computation
Cloud computing addresses how to make right resources available to right computation to improve scaling, resiliency and efficiency of the computation. We argue that cloud computing indeed, is a new paradigm for computati...