Stylometry Detection Using Deep Learning

被引：5

作者：

Surendran, K. ^{[1
]}

Harilal, O. P. ^{[1
]}

Hrudya, P. ^{[1
]}

Poornachandran, Prabaharan ^{[1
]}

Suchetha, N. K. ^{[1
]}

机构：

[1] Amrita Univ, Amrita Sch Engn, Amrita Ctr Cyber Secur Syst & Networks, Amrita Vishwa Vidyapeetham, Amritapuri, India

来源：

COMPUTATIONAL INTELLIGENCE IN DATA MINING, CIDM 2016 | 2017年 / 556卷

关键词：

Readability metrics; Vocabulary richness; Stylometry; CNN; GENDER IDENTIFICATION;

D O I：

10.1007/978-981-10-3874-7_71

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Author profiling is one of the active researches in the field of data mining. Rather than only concentrated on the syntactic as well as stylometric features, this paper describes about more relevant features which will profile the authors more accurately. Readability metrics, vocabulary richness, and emotional status are the features which are taken into consideration. Age and gender are detected as the metrics for author profiling. Stylometry is defined by using deep learning algorithm. This approach has attained an accuracy of 97.7% for gender and 90.1% for age prediction.

引用

页码：749 / 757

页数：9

共 19 条

[1]

[Anonymous], 2010, INT WORKSH SEARCH MI

[2]

[Anonymous], 2013, P INT AAAI C WEB SOC

[3]

[Anonymous], 2012, GENDER PREDICTION TW

[4]

Arroju Mounica, 2014, SORT, V100, P250

[5]

Banchhor Sumit Kumar, COMP TEXT DEPENDENT

[6]

Burger J.D., 2011, DISCRIMINATING GENDE

[7] Author gender identification from text [J].

Cheng, Na ;

Chandramouli, R. ;

Subbalakshmi, K. P. .

DIGITAL INVESTIGATION, 2011, 8 (01) :78-88

[8]

Deitrick W., 2012, Gender identification on twitter using the modified balanced winnow

[9]

Maarten, 2014, DEV AGE GENDER PREDI

[10]

Moseley N, 2014, INT CONF RES CHAL

← 1 2 →