17288

Page 1 of 9

European Journal of Business &

Social Sciences

Available at https://ejbss.org/

ISSN: 2235-767X

Volume 07 Issue 04

April 2019

Available online: https://ejbss.org/ P a g e | 83

Stylometric Analysis: An Approach for Polarity

of the Speaker

MeghaSree, Ramaraju Sruthi

B. Tech Student, Department of CSE, CMR Technical Campus,Kandlakoya Village,

Medchal District, Telangana, India.

Assistant Professor, Department of CSE, CMR Technical Campus,Kandlakoya

Village, Medchal District, Telangana, India.

Abstract- Stylometry is the application of the

study of linguistic style, usually to written

language, but it has successfully been applied to

the speeches of the delegates in analysing the

speech delivered to the audience. Stylometry

grew out of earlier techniques of analyzing texts

for evidence of authenticity, authorial identity,

and other questions.

The goal of this project is to demonstrate and

analyse the speech by the dictator and his

vocabulary and analysing the data in order to

project the statistical patterns. Leverage

Stylometry to identify if shifts in Stylistic patterns

are observed across various speeches, using

Computational tools. In fact, Stylometry has been

used to assess authorship in historic texts.

The crucial analysis with Stylometry is this:

There exist habits for each person, formed

unconsciously, in regards to words’ and

Language usage. These determine the structure,

diversity, and word choice in each person’s

writings, forming a Stylistic signature. Whilst the

writer is conscious of the ideas she writes about,

Stylistic variations go unnoticed. Any deviations

from such often indicates a change of authors.

Keywords:- Stylometry, Data Analysis, Speech,

Behaviour Analysis.

I INTRODUCTION

Stylometry is an area of research where the

analysis can be applied on the user speech

analysis, identifying the behaviour of the speaker.

Stylometric also includes the analysis of the

author identification based on the vocabulary

comparison from author to author.

Here we introduce ‘Stylometry with R’ (stylo), a

flexible R package for the high-level stylistic

analysis of text collections. This package

explicitly seeks to further contribute to the recent

development in the field towards a more

advanced level of replicability and benchmarking

in the field. Stylometry is a multidisciplinary

research endeavor, attracting contributions from

divergent scientific domains, which include

researchers from Computer Science – with a

fairly technical background as well as experts

from the humanities who might lack the

computational skills which would allow them

easy access to the state-of-the-art methods in the

field.

Importantly, this package has the potential to help

bridge the methodological gap luring between

two communities of practice: on the one hand,

stylo’s API allows to set up a complete

processing pipeline using traditional R scripting

and on the other hand, stylo also offers a rich

graphical user interface which allows

non-technical, even novice practitioners to

interface with state-of-the-art methods without

the need for any programming experience.

Stylometry deals with the link between the

writing style in texts and meta-data about those

texts (such as date, genre, gender, authorship).

Researchers in ‘stylochronometry’, for instance,

are interested in inferring the date of the

composition of texts on the basis of stylistic

aspects.

Page 2 of 9

European Journal of Business &

Social Sciences

Available at https://ejbss.org/

ISSN: 2235-767X

Volume 07 Issue 04

April 2019

Available online: https://ejbss.org/ P a g e | 84

Usually stylometric analyses involve a complex,

multi-stage pipeline of (i) pre-processing, (ii)

feature extraction, (iii) statistical analysis, and

finally, (iv) presentation of results, e.g. via

visualization. To this end, researchers presently

have to resort to an ad hoc combination of

proprietary, language dependent tools that cannot

simply be ported across different platforms. Such

solutions are difficult to maintain and exchange

across (groups of) individual researchers,

preventing straightforward replication of analysis

results and reuse of existing code. Stylo, the

package presented, offers a rich, user-friendly

suite of functionality that is ideally suited for fast

exploratory analysis of textual corpora as well as

the classification tasks that are needed in

authorship attribution. The package offers an

implementation of the main methods currently

dominant in the field. Its main advantage

therefore lies in the assimilation of typical (e.g.

reprocessing) procedures from stylometry and

statistical functionality by other, external

libraries. Written in the R language, the source

code and binaries along with package are freely

available from the Comprehensive R Archive

Network, guaranteeing a straightforward

installation process across different platforms

(both UNIX- and Windows-based operating

systems).

The code is easily adaptable and extensible: the

developers therefore continue to welcome user

contributions, feedback and feature requests. We

will first illustrate the functionality of the package

for unsupervised multivariate analysis through

the high-level function stylo (). Secondly, we will

discuss a variety of graphical user interfaces

which we provide for quick exploration of

corpora, especially by novice users or students in

an educational setting, as well as for scholars in

the Humanities without programming

experience. Next, we move on to the function

classify (), implementing a number of supervised

classification procedures from the field of

Machine Learning. Finally, we concisely discuss

the oppose (), rolling.delta () and rolling.classify

() functionality which allow, respectively, to

inspect differences in word usage between two

subsets of a corpus, and to study the evolution of

the writing style in a text.

II RELATED WORK

A Scalable Framework for Stylometric

Analysis Query Processing

Stylometry is the statistical analyses of variations

in the author’s literary style. The technique will

be used in many linguistic analysis applications,

like, author profiling, authorship identification,

and authorship verification. Over the past two

decades, authorship identification has been

extensively studied by researchers in the area of

natural language processing. However, these

studies are generally limited to A small number

of candidate authors, and Documents with similar

lengths.

Similarity Search in a High Dimensional

Space

Since our work involve in characteristic similar

writing styles with respect to a given documents

using the stylometric features, we discuss

techniques for similarity search in an exceedingly

high dimensional space during this subsection.

Indexing and Querying in a Real-Valued Vector

Space. Locality sensitive hashing (LSH) is a

method for approximate similarity search queries

in high dimensional spaces [3]. Gan et al [4]

propose a technique called the collision counting

LSH (C2LSH) method. Using C2LSH, the

collision frequency is employed to estimate the

similarity of two points in a high dimensional

Euclidean space which is more suitable for range

search than E2LSH. They also provide an error

analysis for the range query.

Set Similarity and Outlier Management. The

Hausdorff distance is a well-known measure for

comparing two sets of points in a real-valued

vector space. Specifically, the basic definition of

the Hausdorff distance is given by

H (A, B) = max{h(A,B), h(B,A)},

where h(A,B) is defined as maxa∈ A minb∈B

d(a, b) and d(a, b) is the distance between a and b.

Whoops!
There was a problem loading this page. Retrying...

Page 3 of 9

European Journal of Business &

Social Sciences

Available at https://ejbss.org/

ISSN: 2235-767X

Volume 07 Issue 04

April 2019

Available online: https://ejbss.org/ P a g e | 85

Using this measure, the two sets A and B are

consider similar iff for every element in A, there

is at least one element in B in proximity, and vice

versa.

When we are required to only match A to a subset

of B, we can use the function h(A,B) to perform a

directed distance calculation. We call this variant

the directed Hausdorff distance. Note that h(A,B)

is actually not a distance operation, since the

identity of in discernible and symmetry properties

will not satisfy. However, the term distance is

used in this paper for this kind of function in the

interest of brevity. Other variants of SHD include

the modified Hausdorff distance (MHD) [3] and

partial Hausdorff distance (PHD) [7].

These variants are proposed to address the outlier

sensitivity drawback of SHD [3], [4]. They argue

that even a single point can drastically change the

SHD value and propose two different approaches

to handle outliers.

Since our work involve characteristic same

writing styles with respect to a given documents

using the stylometric features, we discuss

techniques for the similar search in a high

dimensional space in this subsection. Indexing

and Querying in a Real-Valued Vector Space

A per Nathaniel Latte - Stylometry is the study of

linguistic style, this means watching at patterns in

the given language to stipulate rules or

characteristics of the subject of study. Stylometry

is often used to regulate authorship to anonymous

manuscripts, but the principles of Stylometry can

also be used in other areas such as the analysis of

music. Stylometrists search for a clear

measurable attribute that can be used to draw

definitive conclusions about an author. It is

possible however, that such a feature does not

exist. However, as the searches progresses,

researchers find the statistical attributes and

develop tools as, they use conjunction with each

other, allow very strong conclusions to be drawn

in authorship disputes. There are three

contrasting categories which general stylometry

can be broken into. These are authorship

attribution, characterization, and verification.

Authorship attribution is determining the correct

author out of a small group of authors.

Authorship Characterization involves

determining the physical characteristics of an

author such as age, gender, or race.

Authorship verification is determining if a

document was written by a specific individual.

The differences between verification and

attribution are much nuanced. If the reader

desires to find out regarding the variations, the

paper Authorship verification for short messages

using Stylometry (Computer, Information and

Telecommunication Systems (CITS), 2013

International Conference on. IEEE, 2013) By

Brocardois a good start. Most research in

stylometry falls into a category of attribution,

with verification being the smallest amount

developed, having been studied almost

exclusively in the context of plagiarism.

Stylometric tests are generally addressed at long

documents being unreliable on short documents.

A long document is a fairly general term often

dependent upon the study. Short documents are