ArticlePDF Available

Quantifying Opinion Strength: A Neutrosophic Inference System for Smart Sentiment Analysis of Social Media Network

July 2022
Applied Sciences 12(15):7697

DOI:10.3390/app12157697

License
CC BY 4.0

Authors:

Reem Essameldin

Alexandria University

Saad Darwish

Institute of graduate studies and research, Egypt

The contemporary speed at which opinions move on social media makes them an undeniable force in the field of opinion mining (OM). This may cause the OM challenge to become more social than technical. This is when the process can determinately represent everyone to the degree they are worth. Nevertheless, considering perspectivism can result in opinion dynamicity. Pondering the existence of opinion dynamicity and uncertainty can provide smart OM on social media. This study proposes a neutrosophic-based OM approach for Twitter that handles perspectivism, its consequences, and indeterminacy. For perspectivism, a social network analysis (SNA) was conducted using popular SNA tools (e.g., Graphistry). An influence weighting of users was performed using an artificial neural network (ANN) based on the SNA provided output and people’s reactions to the OM analyzed texts. The initiative adoption of neutrosophic logic (NL) to integrate users’ influence with their OM scores is to deal with both the opinion dynamicity and indeterminacy. Thus, it provides new uncertainty OM scores that can reflect everyone. The OM scores needed for integration were generated using TextBlob. The results show the ability of NL to improve the OM process and accurately consider the innumerable degrees. This will eventually aid in a better understanding of people’s opinions, helping OM in social media to become a real pillar of many applications, especially business marketing.

The proposed NL-based OM model.

…

The constructed directed graph using different SNA tools.

…

The training and scoring processes of the constructed ANN.

…

Correlation between users' scores and their tweets reactions.

…

(a) A training performance of 9.6461 with 100 Samples, (b) a training performance of 4.1030 with 10,000 Samples.

…

Figures - available via license: Creative Commons Attribution 4.0 International

Content may be subject to copyright.

Available via license: CC BY 4.0

Content may be subject to copyright.

Citation: Essameldin, R.; Ismail,

A.A.; Darwish, S.M. Quantifying

Opinion Strength: A Neutrosophic

Inference System for Smart Sentiment

Analysis of Social Media Network.

Appl. Sci. 2022,12, 7697. https://

doi.org/10.3390/app12157697

Academic Editors: Adegboyega Ojo

and Rizun Nina

Received: 30 May 2022

Accepted: 29 July 2022

Published: 30 July 2022

Publisher’s Note: MDPI stays neutral

with regard to jurisdictional claims in

published maps and institutional afﬁl-

iations.

Licensee MDPI, Basel, Switzerland.

This article is an open access article

distributed under the terms and

conditions of the Creative Commons

Attribution (CC BY) license (https://

creativecommons.org/licenses/by/

4.0/).

applied

sciences

Article

Quantifying Opinion Strength: A Neutrosophic Inference

System for Smart Sentiment Analysis of Social Media Network

Reem Essameldin 1, Ahmed A. Ismail 2and Saad M. Darwish 1, *

1Department of Information Technology, Institute of Graduate Studies and Research, Alexandria University,

163 Horreya Avenue, El-Shatby, Alexandria 21526, Egypt; igsr.reemessameldin@alexu.edu.eg

2The Higher Institute of Computers and Information Systems, Abo Qir, Alexandria 21913, Egypt;

gisapp13@gmail.com

*Correspondence: saad.darwish@alexu.edu.eg

Abstract:

The contemporary speed at which opinions move on social media makes them an un-

deniable force in the ﬁeld of opinion mining (OM). This may cause the OM challenge to become

more social than technical. This is when the process can determinately represent everyone to the

degree they are worth. Nevertheless, considering perspectivism can result in opinion dynamicity.

Pondering the existence of opinion dynamicity and uncertainty can provide smart OM on social

media. This study proposes a neutrosophic-based OM approach for Twitter that handles perspec-

tivism, its consequences, and indeterminacy. For perspectivism, a social network analysis (SNA)

was conducted using popular SNA tools (e.g., Graphistry). An inﬂuence weighting of users was

performed using an artiﬁcial neural network (ANN) based on the SNA provided output and people’s

reactions to the OM analyzed texts. The initiative adoption of neutrosophic logic (NL) to integrate

users’ inﬂuence with their OM scores is to deal with both the opinion dynamicity and indeterminacy.

Thus, it provides new uncertainty OM scores that can reﬂect everyone. The OM scores needed

for integration were generated using TextBlob. The results show the ability of NL to improve the

OM process and accurately consider the innumerable degrees. This will eventually aid in a better

understanding of people’s opinions, helping OM in social media to become a real pillar of many

applications, especially business marketing.

Keywords: social network analysis; artiﬁcial neural networks; neutrosophic logic; opinion mining

1. Introduction

Nowadays, the fact that social media is the main source of digital marketing and

market research information (e.g., news and reviews) is solidiﬁed [

]. With billions of

active users on different online social networks (OSNs), people have started to eliminate

global barriers by sharing their thoughts, opinions, and feelings toward everything [

The core strength of these OSNs is their inﬂuence; companies can communicate with their

customers with positive content to boost motivation towards their products or services.

Interestingly, people rather than companies are proved to be the leading engine of inﬂuence

on OSNs; they can drive public orientation towards anything in a matter of seconds [

In either case, opinion mining (OM) or sentiment analysis (SA) is essential to analyze

opinions, for companies to obtain insight into how their marketing strategies performed,

how people on OSNs talk about them, and then take corrective actions afterward to improve

their business [6].

Opinions are expressed by humans (i.e., opinion holders about an entity or features of

an entity at a given time) [

]; business owners, who aim at improving their market image,

pay more attention to searching for opinion holders of good impact on OSNs to spread

opinions of positive orientations about their business entities and their features [

]. Social

network analysis (SNA) was applied to OSNs to highlight inﬂuencers for businesses to

Appl. Sci. 2022,12, 7697. https://doi.org/10.3390/app12157697 https://www.mdpi.com/journal/applsci

Appl. Sci. 2022,12, 7697 2 of 20

spread positive opinions of their business [

]. Using the graph and network theory, SNA is

one way to study the importance of users in their social networks. The centrality measure in

SNA is one primary assessment for detecting inﬂuential nodes (i.e., users) in a given graph

network [

]. However, this sort of action can increase the diffusion of positive opinions

with no effect on the main process; OM deals with opinion texts only [1].

The subjective nature of opinions makes them subject to many types of uncertainty

when being automatically analyzed. For example, opinions have gradient polarity; two

positive texts are not positive to the same degree. Moreover, undecided polarity can happen

when text polarity is at an equal distance between two polarity classes. At that instant, the

machine makes the approximate or dominant choice (e.g., neutral class). Likewise, many

neutral classiﬁed opinions are undecided (e.g., having the same opposite polarity) but such

a class is not considered in OM classiﬁcation [

]. These innumerable degrees reﬂect reality

and are found in social media texts, which then need to be considered for more accurate

and real OM results. More than that, when individuals perform text rating, this may cause

the generation of different rates for the same texts based on the observers’ perspective.

Opinion dynamics on OSNs is one possible result of perspectivism, thus correlated with

SNA in the determinacy of users’ importance and trust degree [7,9,10].

All the above-mentioned cases can be easily detected and solved by humans, but

hardly processed by machines [

]. Leaving aside its unfamiliar implementation in OM,

the nature of neutrosophic logic (NL) is highly integrated with how humans think, where

an indeﬁnite environment is a human’s ordinary space to draw a conclusion or make a

judgment due to incomplete knowledge. Furthermore, NL is malleable in terms of accepting

different values from observers. Thus, NL can acquire some mental ability for the OM

process to become smart. In NL, each object in a certain universe has a degree of

truth (T),

a degree of indeterminacy (

), and a degree of falsity

(F)

, where

are standard or

non-standard real subsets of

]−0, 1+[

. Such a classiﬁcation might help in determining the

percent of indeterminacy in a text’s polarity [9].

The main objectives of this study are to reduce social bias through algorithmically

certain and more accurate OM classiﬁcation results beﬁtting trust. The proposed model can

improve the process of OM in OSNs by highlighting the most irritating technical problems

that are caused by the social tendency of the application domain.

The remainder of this paper is planned in the following way. In Section 2, social

media-based research is classiﬁed and brieﬂy discussed in a literature-based approach.

Section 3highlights the research problem for Section 4to deﬁne how the proposed model

is intended to solve it. The required validations and their resulting analysis are presented

and elucidated in Section 5. Conclusions are drawn in Section 6.

2. Related Work

Research that is based on analyzing social media data are gaining massive

attention [4,6].

In the literature, this research type is performed to serve many applications (e.g., market,

health care, etc.), and they are mostly classiﬁed into structural-based and content-based

analyses [

]. The structural-based analysis deals with the main social network structure,

studies nodes (i.e., users) interactions, and the network topology. The content-based

analysis deals with content being created by nodes and shared on social media [

]. Figure 1

shows the classiﬁcation of social media data-based research.

In marketing applications, business owners and researchers are concerned about the

structural-based analyses that include SNA to ﬁnd inﬂuencers [

]. In line with that, in

2017, most research found OSNs’ inﬂuencers based on graph theory by measuring network

topology (e.g., degree of centrality, betweenness, etc.) [

]. Jianqiang et al. [

] proposed

measuring inﬂuence based on considering not only the structural-based analysis of social

media data (i.e., graph theory), but also the inﬂuence of users’ tweets by considering

retweets, replies, and favorite counts. They believed that the content of tweets itself

can inﬂuence people as much as their authors. They tested their proposed model, and

it was found to be a better method than the compared methods. In 2020, concerning

Appl. Sci. 2022,12, 7697 3 of 20

the community detection under the same analysis type, Oueslati et al. [

] highlighted the

problem of detecting opinion leaders on dynamic social graphs. They attempted to consider

the dynamic nature of online social networks (OSNs) while detecting opinion leaders on

social media. They proposed a new model that collected Facebook posts and then ﬁltered

them based on the included opinion words and the text type (i.e., status). They considered

posts important when having higher opinion words and social reactions. Accordingly,

inﬂuencers were the ones whose posts had the highest combined score. Experiments on real

data collected from Facebook were performed. The validation of the model was compared

with some previous work, and the results showed good performance of this model when

considering the dynamic nature of the network.

Appl. Sci. 2022, 12, 7697 3 of 21

Figure 1. Social media data-based research classification in the literature.

In marketing applications, business owners and researchers are concerned about the

structural-based analyses that include SNA to find influencers [10]. In line with that, in

2017, most research found OSNs’ influencers based on graph theory by measuring net-

work topology (e.g., degree of centrality, betweenness, etc.) [4,11]. Jianqiang et al. [12]

proposed measuring influence based on considering not only the structural-based analy-

sis of social media data (i.e., graph theory), but also the influence of users’ tweets by con-

sidering retweets, replies, and favorite counts. They believed that the content of tweets

itself can influence people as much as their authors. They tested their proposed model,

and it was found to be a better method than the compared methods. In 2020, concerning

the community detection under the same analysis type, Oueslati et al. [7] highlighted the

problem of detecting opinion leaders on dynamic social graphs. They attempted to con-

sider the dynamic nature of online social networks (OSNs) while detecting opinion lead-

ers on social media. They proposed a new model that collected Facebook posts and then

filtered them based on the included opinion words and the text type (i.e., status). They

considered posts important when having higher opinion words and social reactions. Ac-

cordingly, influencers were the ones whose posts had the highest combined score. Exper-

iments on real data collected from Facebook were performed. The validation of the model

was compared with some previous work, and the results showed good performance of

this model when considering the dynamic nature of the network.

It was found that the isolated application of one analysis, whether it was structural

or content-based, can cause information incompleteness, essential patterns, and

knowledge loss [4]. This caused a few researchers to combine both analyses for different

application purposes. In 2021, Jin et al. [13] attempted to combine both the content-based

analysis (i.e., SA) with the structural-based analysis (i.e., SNA) by designing a new senti-

ment link analysis using a graph network to predict users’ attitudes towards an entity.

They considered the problem of determining users’ attitudes towards entities without the

normal analysis of text sentiment. They tried to solve the problem of the undecided po-

larity of tweets posted by their authors on social media due to the short text or unclear

wording to retrieve users’ real attitudes. They also tried to predict the hidden attitude

when users did not share their opinions on social media. They modeled the information

network to retrieve unknown sentiment links based on users’ social relationships, user

attributes, and movie attributes. Experiments were conducted using movies reviewed from

Weibo gaming proving the effectiveness of this method on some state-of-art methods.

In the same year, Chauhan et al. [14] highlighted the importance of predicting elec-

tion results based on three approaches by surveying 38 papers on election prediction. The

three approaches were: the volumetric approach (counts of posts, likes, etc.); the content-

based analysis in the form of the SA approach (polarity of posts); and the structural-based

analysis in the form of SNA (measure centrality of supporters). They found that most re-

search depended on SA, either alone or combined with a volumetric approach. Only one

paper combined the three approaches. They concluded the need for more efforts in this

Figure 1. Social media data-based research classiﬁcation in the literature.

It was found that the isolated application of one analysis, whether it was structural or

content-based, can cause information incompleteness, essential patterns, and knowledge

loss [

]. This caused a few researchers to combine both analyses for different application

purposes. In 2021, Jin et al. [

] attempted to combine both the content-based analysis

(i.e., SA) with the structural-based analysis (i.e., SNA) by designing a new sentiment

link analysis using a graph network to predict users’ attitudes towards an entity. They

considered the problem of determining users’ attitudes towards entities without the normal

analysis of text sentiment. They tried to solve the problem of the undecided polarity of

tweets posted by their authors on social media due to the short text or unclear wording

to retrieve users’ real attitudes. They also tried to predict the hidden attitude when users

did not share their opinions on social media. They modeled the information network to

retrieve unknown sentiment links based on users’ social relationships, user attributes, and

movie attributes. Experiments were conducted using movies reviewed from Weibo gaming

proving the effectiveness of this method on some state-of-art methods.

In the same year, Chauhan et al. [

] highlighted the importance of predicting election

results based on three approaches by surveying 38 papers on election prediction. The three

approaches were: the volumetric approach (counts of posts, likes, etc.); the content-based

analysis in the form of the SA approach (polarity of posts); and the structural-based analysis

in the form of SNA (measure centrality of supporters). They found that most research

depended on SA, either alone or combined with a volumetric approach. Only one paper

combined the three approaches. They concluded the need for more efforts in this ﬁeld to

produce a more valid and acceptable model for election result prediction (e.g., to detect

spam accounts, sarcasm, etc.).

Regarding the implementation of the NL technique in the literature, it was found

to be applied in many ﬁelds (e.g., image processing and disease diagnosis) with no real

application to SA not long ago [

]. Some researchers have investigated the signiﬁcance of

NL by conducting theoretical comparisons with other existing logics (e.g., intuitionistic

logic and fuzzy logic) [15–17].

Due to the low implementation rate of NL, there are a lack of ﬁndings for a speciﬁc

software tool for NL. Consequently, a few researchers have started to suggest an imple-

Appl. Sci. 2022,12, 7697 4 of 20

mentation method for applying NL in practice [

]. In 2012, Ansaria et al. [

] mentioned the

problem of not having any available software for NL. They presented full-detailed steps for

generating an NL classiﬁer based on the fuzzy toolbox of MATLAB. It followed the same

idea of constructing three fuzzy inference systems (FIS) representing each component of

NL. They also illustrated the ambiguity cases in detail for the Iris dataset when applying

fuzzy and NL systems, showing how professionally NL can deal with ambiguity cases. In

the same direction, in 2016, Basha et al. [

] suggested the utilization of a knowledge-based

rule-based system due to the close resemblance between human thinking and rule-based

approaches. They proposed a neutrosophic rule-based system to handle uncertainty, in

particular, ambiguity due to the overlap areas in classiﬁcation. The proposed model desig-

nates rules and non-overlap membership functions for each NL output component. Rules

were trained and tested on three datasets (e.g., the Iris dataset). A comparison with a fuzzy

system was conducted to prove the ability of the NL system to handle ambiguity with

better accuracy.

In 2018, Bhutani et al. [

] highlighted the importance of rule-based classiﬁcation

using fuzzy logic for its ability to handle interpretation and its weakness in handling

uncertainty. The authors in [

] followed the same concept and steps as in [

]. They

constructed an NL classiﬁer on the same line as their fuzzy classiﬁer. The difference was in

designing the membership functions. In NL, the output must be represented in triple format

components. For each component, they designed non-overlapping membership functions

for both input and output and the component rules. The constructed NL classiﬁcation

model was practiced on an appendicitis dataset and then compared with the ordinary fuzzy

classiﬁer as a performance test. The comparison demonstrated the superiority of the NL

classiﬁer in handling ambiguity in the data classiﬁcation.

In dealing with the uncertainty and OM, in 2017, Smarandache et al. [

] attempted

to express the importance of the NL in dealing with uncertainties and how it can handle

idea dynamicity. They applied NL in an election process where blind and null votes

might represent a high percentage and needed to be processed. They proposed a reﬁning

process based on minimizing the rate of indeterminacy and increasing the truth and falsity

rates in returns, thus minimizing uncertainties. Using NL, they succeeded in ﬁnding and

effectively reﬁning these types of votes. In 2019, Smarandache et al. [

] addressed the

problem of word similarity. They attempted to design a new word similarity measure

based on sentiment results obtained from SentiWordNet 3.0. This considered the challenge

of multi-meaning words by measuring the semantic distance from a seed word using a

neutrosophic approach. They proposed an NL method for classifying the sentiment of

words by measuring distances to seed words representing each standard polarity class.

They applied Hamming distance, Euclidean distance, and Intuitionistic Euclidean distance

to evaluate the accuracy of the method where promising results were obtained.

In 2020, Kandasamya et al. [

] suggested a reﬁned process for SA polarity results from

TextBlob to handle the problem of indeterminacy in polarity. They proposed a multi-reﬁned

neutrosophic set where polarity scores resulted are reﬁned into seven polarity classes (i.e.,

strong positive, positive, indeterminate positive, indeterminate, indeterminate negative,

negative, and strong negative). Another two methods were applied, where polarity scores

were classiﬁed into ﬁve and three classes, respectively. A comparative study was conducted

between their model and the two other used methods. Tests were performed on 10 different

datasets to see how well the three methods worked at evaluating them. The results showed

that the proposed reﬁned method was the best.

In conjunction with the continuous production of social media-based research, this

work combined both structure and content-based methods by utilizing a neutrosophic-

based OM approach that can provide each author with a polarity score for his text that

depends on his inﬂuence level. A new element to the basic ﬁve opinion elements that

represented the inﬂuence level was added. This model applies a novel classiﬁcation of the

opinion holders into four types based on their centrality measures and the reactions to their

texts using an artiﬁcial neural network (ANN). SNA was performed using several software

Appl. Sci. 2022,12, 7697 5 of 20

tools that are available online to provide the required information about authors’ topologies

in their OSNs. People’s opinions and text polarity scores are combined for the ﬁrst time in

this model. It also takes into account text indeterminacy and dynamicity with NL.

3. Problem Deﬁnition

On OSNs, each of the basic opinion elements (

aij

) spearheads the orientation

of opinions (

ooi jkl

) to which they belong. At a given time (

), billions of opinion holders (

)

share their opinions at tremendous speed about any entity (

) or/and its features (

aij

); OM

must automatically deal with the frequent increase in opinions and their orientation (

ooi jkl

)

change over time [

]. One reason for the orientation change is the

inﬂuence; people on

OSN can establish credibility in areas of wide audience interest due to their personality,

knowledge, or simply for sharing relatable content. They can have different observations

of the same entity, leaving the decision to the audience to agree with whom they trust more.

Nevertheless, OM treats opinions as pure text with the same importance, whether they are

expressed by a professional, expert, inﬂuencer, spammer, or ordinary person. Contrary to

the norm, opinion holders in the eye of OM are equally likely threaten the credibility of

opinions and the validity of results. Back to the content being processed, OM can process

features of an entity when more detailed opinions are important, and only the entity when

detailed opinions are less important. However, writing opinions on OSNs in a spoken

language increases the risk of content uncertainty as well as the hardiness of determining

its main scope.

These issues doubt the ability of OM on OSNs in reﬂecting reality providing low-

quality information-based results for OM beneﬁciaries and decision makers. Accordingly,

improving the process of OM on OSNs became an insistence. In the achievement of such,

the OM process should take into consideration the inﬂuence of users and their perspective

power as well as the uncertainty of texts and their impact on result efﬁciency. A summary

of the problems to be solved in this study is as follows:

The compulsory dependency on low-quality information for the OM process and its

reﬂection on providing invalid results for decision making;

The scarcity of parallel processing of perspectivism (i.e., users’ credibility) with the

main OM process;

The need for effective ways to determine and numerically represent users’ credibility;

The inefﬁcient consideration of opinion dynamics in generating a sensitive

consensus opinion;

- The continuous need for decreasing ambiguity in opinion texts;

The absence of a methodical integration between polarity scores and text perspectivism

in the process of OM to provide a polarity score that reﬂects real intentions.

4. Proposed Model

The above-mentioned problems caution the ability of OM, in its current state, to be

applied to OSNs. The main shortage is in the sedulity to use the same opinion elements

while being applied to OSNs and their environmental uncertainty. The proposed model

aims to improve the effectiveness of applying OM to Twitter. To solve the mentioned

problems, we should readapt the opinion elements to accommodate the application domain

properties. Accordingly, we need to introduce new elements to qualify the OM process

on OSNs that are speciﬁcally related to opinion holders’ hallmarks and social reactions

to their actions. Other than that, we must solve common uncertainty problems that can

improve the opinion classiﬁcation process. The proposed model mainly focuses on all the

previously mentioned problems while holding the following contributions:

The proposed model suggests adding a new element (assume:

wkl

) to the ﬁve elements

of opinion, describing the importance of opinion holders and their reactions to their

opinions. This element takes into consideration the impact of the opinion holder and

his reaction to his opinion on the assigned opinion orientation. Importance weighting

should be applied to opinion holders so that they are provided weights based on their

Appl. Sci. 2022,12, 7697 6 of 20

authority over the audience. As such, perspectivism can be practically represented in

the main OM process;

The users’ weighting method is proposed in this model, which depends on apply-

ing SNA and ANN. A comparative analysis of three famous SNA tools must be

conducted to adopt the most applicable one. ANN is applied to rank users based

on their centrality measure produced by the SNA tool as well as the reaction-based

features of users’ texts (i.e., likes, shares, etc.). Weights are provided based on users’

ranks; the top-ranked is the most weighted and vice versa. ANN was chosen for

being efﬁcient in dealing with the complicated behavior of humans that could not be

mathematically represented;

The innovative adoption of NL is to integrate the new elements with the other tra-

ditional elements of opinion. Moreover, NL adoption hybrids the process of OM,

providing more accurate polarity scores through performing the OM combining lex-

icon with machine learning (ML) (i.e., TextBlob and NL). Finally, NL was proven

to effectively deal with uncertainty especially opinion ambiguity and dynamicity.

Figure 2presents the proposed model and its components. The phases of the proposed

model are described as follows:

Appl. Sci. 2022, 12, 7697 7 of 21

Figure 2. The proposed NL-based OM model.

4.1. Data Collection Phase

Any model requires data to work on and test its validity. For OM, this phase is es-

sential to identify most of the opinion elements (i.e., ℎ, , , and ). In this proposed

model, Twitter is the chosen OSN, and thus, the Twitter API was used to collect the nec-

essary data. For the proposed model and adding to the traditional data required in any

OM process, data about opinion holders and their tweets’ reaction-based features are to

be essentially required for collection. The previously collected data in [10] were used for

this work due to the lack of availability of data that include both aspects of opinion hold-

ers, and their tweets’ features, along with the main opinion texts. Accordingly, for this

model, the data required to represent opinion elements were as follows:

- Opinion text in the English language, per user;

- , : the opinion entity is the World Football Cup 2018 and all its possible aspects

(e.g., video assistant referee (VAR));

- ℎ: indicates username of the opinion holder;

- : opinions that were collected during the period from 14 June 2018 till 15 July 2018,

and;

Figure 2. The proposed NL-based OM model.

Appl. Sci. 2022,12, 7697 7 of 20

4.1. Data Collection Phase

Any model requires data to work on and test its validity. For OM, this phase is essential

to identify most of the opinion elements (i.e.,

aij

, and

). In this proposed model,

Twitter is the chosen OSN, and thus, the Twitter API was used to collect the necessary data.

For the proposed model and adding to the traditional data required in any OM process,

data about opinion holders and their tweets’ reaction-based features are to be essentially

required for collection. The previously collected data in [

] were used for this work due

to the lack of availability of data that include both aspects of opinion holders, and their

tweets’ features, along with the main opinion texts. Accordingly, for this model, the data

required to represent opinion elements were as follows:

- Opinion text in the English language, per user;

-ei

aij

: the opinion entity is the World Football Cup 2018 and all its possible aspects

(e.g., video assistant referee (VAR));

-hk: indicates username of the opinion holder;

-tl

: opinions that were collected during the period from 14 June 2018 till 15 July 2018,

and;

The contribution support data that include: follower/following list of

and the likes,

retweets, and replies counts for their collected opinion tweet.

4.2. Users Weighting Process

This contribution phase is divided into two main steps: SNA then ANN ranking and

weighting processes. Data collected from the ﬁrst phase about the newly added elements is

mainly required to execute this phase. Follower/following lists and tweets’ features are

individually used as follows:

(1)

Social Network Analysis (SNA)

This step works with follower/following lists of opinion holders. Using SNA, users

in a given social network can be provided some centrality measures representing their

importance in this network. Owning higher centrality measures indicates more central,

inﬂuential, and powerful users [

]. The most considered centrality measures in this work

are degree, betweenness, and closeness centrality. They measure the popularity of nodes

through counting connections, how users control information diffusion in the network,

and how quickly information spreads from users, respectively [

]. By applying some

available SNA tools and using the collected follower/following lists, a graph of users can

be constructed. In such a graph, a user is represented as a node, symbolized as “

”, and

his relations between other users are edges, symbolized as “

” per each, with directions,

so-called directed graph “

”. Moreover, centrality measures of nodes can be obtained. The

directed graph and centrality measures are deﬁned as [24]:

G=(V,E)(1)

where

is the social network graphically represented, as shown in Figure 3.

is the set

of nodes representing users in the OSN: V= {u

. . .

}, and

is the set of edges

representing directed relations between the graphically represented nodes in the OSN:

E= {e1,e2,e3, . . . , em}

. If two users (e.g.,

and

) follow each other, then a directed edge

between the two users is constructed: eu1u2∈E.

Cd−(u) = 



→

Ni



(2)

where

Cd−(u)

is the degree centrality (out-degree) of node

representing the number of

outgoing edges from a node, and

→

Ni={jeV:(i,j)eE}

is a set of nodes that node

connected to [12].

Bet(u) = ∑

r6=u6=w∈V

|{gr w(u)}|

|{gr w}| (3)

Appl. Sci. 2022,12, 7697 8 of 20

where

Bet(u)

is the betweenness centrality of node

|{gr w}|

denotes the number of

shortest paths from node

to node

, and

|{gr w(u)}|

denotes the number of the shortest

paths from node rto node wthrough node u.

Col(u) = 1

N+1∑

w∈V,w6=u

gu,w(4)

where

Col(u)

is the closeness centrality of node

is the number of nodes in

, and

gu,w

is the length of the shortest paths between the uth node and the rest of the network.

Appl. Sci. 2022, 12, 7697 9 of 21

Figure 3. The constructed directed graph using different SNA tools.

A comparative analysis of three famous SNA software tools (i.e., Graphistry, Cyto-

scape, and the University of California at Irvine network (UCINET)) was conducted to

choose the most suitable tool for this proposed work. According to our view and based

on the evaluation process conducted in [4], Graphistry is the best relevant SNA software

tool to adopt. Compared with the other tools, it was found to be the best in terms of visu-

alization, scalability, and ease of use. Figure 3 shows the different representations of our

directed graph using the three mentioned SNA software tools. As illustrated in Figure 3,

we can easily identify bridges and popular users in Graphistry and Cytoscape while noth-

ing can be identified using UCINET. Nodes in Graphistry are represented with large circle

sizes with a large degree of centrality measures. The larger the degree of centrality of a

node, the larger the circle size and vice versa. Moreover, Graphistry was easier for loading

the data and building the directed graph.

(2) Artificial Neural Network Ranking Process

In this step, the collected data about tweets’ reaction features (i.e., likes, counts, etc.)

is combined with the centrality measures of their opinion holders obtained from the SNA

process to help rank opinion holders based on their tweet’s influence as well as their top-

ological influence in the social network. Opinion holders obtain scores from 1 to 100.

When centrality measures are high or/and their tweets obtain high reactions, then opinion

holders obtain a high score and are highly ranked. ANN is used for this step; Figure 4

shows the steps of the ANN scoring process. ANN adoption was due to the complexity of

this behavioral data to be mathematically represented. Figure 5 shows, in practice, the

correlation between a sample data of action-based records (X-axis) and the resultant users’

score (Y-axis) when plotted. It can be noticed that, for example, authors of low action-

based tweets’ counts can highly score and vice versa. Thus, there is no certain guidance

rule for scoring users based on their tweets’ action-based counts.

Figure 3. The constructed directed graph using different SNA tools.

A comparative analysis of three famous SNA software tools (i.e., Graphistry, Cytoscape,

and the University of California at Irvine network (UCINET)) was conducted to choose

the most suitable tool for this proposed work. According to our view and based on the

evaluation process conducted in [

], Graphistry is the best relevant SNA software tool to

adopt. Compared with the other tools, it was found to be the best in terms of visualization,

scalability, and ease of use. Figure 3shows the different representations of our directed

graph using the three mentioned SNA software tools. As illustrated in Figure 3, we can

easily identify bridges and popular users in Graphistry and Cytoscape while nothing can

be identiﬁed using UCINET. Nodes in Graphistry are represented with large circle sizes

with a large degree of centrality measures. The larger the degree of centrality of a node, the

larger the circle size and vice versa. Moreover, Graphistry was easier for loading the data

and building the directed graph.

(2)

Artiﬁcial Neural Network Ranking Process

In this step, the collected data about tweets’ reaction features (i.e., likes, counts, etc.)

is combined with the centrality measures of their opinion holders obtained from the SNA

process to help rank opinion holders based on their tweet’s inﬂuence as well as their

topological inﬂuence in the social network. Opinion holders obtain scores from 1 to 100.

When centrality measures are high or/and their tweets obtain high reactions, then opinion

holders obtain a high score and are highly ranked. ANN is used for this step; Figure 4

shows the steps of the ANN scoring process. ANN adoption was due to the complexity

of this behavioral data to be mathematically represented. Figure 5shows, in practice, the

correlation between a sample data of action-based records (X-axis) and the resultant users’

Appl. Sci. 2022,12, 7697 9 of 20

score (Y-axis) when plotted. It can be noticed that, for example, authors of low action-based

tweets’ counts can highly score and vice versa. Thus, there is no certain guidance rule for

scoring users based on their tweets’ action-based counts.

Appl. Sci. 2022, 12, 7697 10 of 21

Figure 4. The training and scoring processes of the constructed ANN.

Figure 5. Correlation between users’ scores and their tweets reactions.

A trial and error approach was followed and resulted in a constructed feed-forward

ANN with 10 neurons in its hidden layer. In the training process, a sample of 100 to 10,000

records per input was applied to improve training performance and decrease scoring errors.

Figure 4. The training and scoring processes of the constructed ANN.

Appl. Sci. 2022, 12, 7697 10 of 21

Figure 4. The training and scoring processes of the constructed ANN.

Figure 5. Correlation between users’ scores and their tweets reactions.

A trial and error approach was followed and resulted in a constructed feed-forward

ANN with 10 neurons in its hidden layer. In the training process, a sample of 100 to 10,000

records per input was applied to improve training performance and decrease scoring errors.

Figure 5. Correlation between users’ scores and their tweets reactions.

Appl. Sci. 2022,12, 7697 10 of 20

A trial and error approach was followed and resulted in a constructed feed-forward

ANN with 10 neurons in its hidden layer. In the training process, a sample of

100 to

10,000 records

per input was applied to improve training performance and decrease

scoring errors.

Figure 6illustrates the impact of applying 100 and 10,000 training samples on the

ANN process error, where error seemed to decrease as training samples increased. Another

observation is the dependency on the out-of-degree measure rather than other centrality

measures. The output of the constructed ANN is a user score of 100; a user with a score of

100 is a highly ranked user, while one with a score of 1 is a lowly ranked one. These output

scores are normalized to represent users’ important weighting; high-scoring users are highly

ranked with a higher importance weight than others in the same social network. Users’

importance weighting results in classifying opinion holders into 4 main classes or types as

follows: Micro, Macro, Mega, and A-Listers Inﬂuencers [

–

]. Figure 7summarizes how

opinion holders are classiﬁed in this proposed work and their inﬂuence levels.

Appl. Sci. 2022, 12, 7697 11 of 21

Figure 6 illustrates the impact of applying 100 and 10,000 training samples on the

ANN process error, where error seemed to decrease as training samples increased. An-

other observation is the dependency on the out-of-degree measure rather than other cen-

trality measures. The output of the constructed ANN is a user score of 100; a user with a

score of 100 is a highly ranked user, while one with a score of 1 is a lowly ranked one.

These output scores are normalized to represent users’ important weighting; high-scoring

users are highly ranked with a higher importance weight than others in the same social net-

work. Users’ importance weighting results in classifying opinion holders into 4 main classes

or types as follows: Micro, Macro, Mega, and A-Listers Influencers [25–28]. Figure 7 sum-

marizes how opinion holders are classified in this proposed work and their influence levels.

Figure 6. (a) A training performance of 9.6461 with 100 Samples, (b) a training performance of 4.1030

with 10,000 Samples.

Figure 6.

(

) A training performance of 9.6461 with 100 Samples, (

) a training performance of

4.1030 with 10,000 Samples.

Appl. Sci. 2022,12, 7697 11 of 20

Appl. Sci. 2022, 12, 7697 12 of 21

Figure 7. Opinion holders’ classification based on their influence level.

- Micro influencers: This category is of a low influence level that may include: personal

users, secondary actors, retweeters, or silent followers. These users exhibit poor be-

havior in their social networks. Neither active nor sparing, they use their account

when they like to and for their purposes (i.e., entertainment, news, and learning).

Thus, Micro influencers can possess low reactions to their writings and low centrality

measures as shown in Figure 7;

- Macro influencers: Their influence level lies between low and moderate influence. It

includes actors with important content, builders, or even trolls. They work on build-

ing and growing their relationships and increasing their social network engagement

through creating interesting content or even inflammatory conversation. Thus, they

can possess high reactions to their writings as shown in Figure 7. They can become

mega influencers with time based on their ability to gain audience trust;

- Mega Influencers: This category’s influence level can lie between moderate and high

influence levels. It may include business users, brokers, and newscasters. They are

followed by a large sector for being the source of information. Thus, they possess

high centrality measures as shown in Figure 7. They record an active presence on

social media, providing service, marketing, advertising, etc.;

- A-list influencers or potential influencers: They own the highest influence level. They

are extremely popular and have between thousands and millions of followers. They

include: celebrities, the most recognizable people on earth that tend to act, sing, play

football, etc.; or professionals who have grown a strong brand for themselves for

sharing useful information about topics of professional interest, fostering interaction,

and being followed by many. Thus, they possess both high reactions and centrality

measures as shown in Figure 7.

4.3. Opinion Mining Process

This phase deals with the opinion texts of the data collected in the first phase. It in-

cludes two main steps: text preprocessing and opinion classification. A lexicon technique

(i.e., TextBlob) is to be applied to the collected tweets. TextBlob is a natural language pro-

cessing (NLP) Python library that returns two values for SA: polarity and subjectivity,

with a standard range of [− 1.0,1.0], where negative values refer to negative statements

and positive ones to positive statements. In our work, TextBlob was utilized for the two

mentioned steps of this phase. The reason for choosing a lexicon classifier, TextBlob in

particular, is owing to the previous intention to perform a hybrid classification of tweets

by combining lexicon, in this case, TextBlob, with ML, which is NL in the final phase.

Figure 7. Opinion holders’ classiﬁcation based on their inﬂuence level.

Micro inﬂuencers: This category is of a low inﬂuence level that may include: personal

users, secondary actors, retweeters, or silent followers. These users exhibit poor

behavior in their social networks. Neither active nor sparing, they use their account

when they like to and for their purposes (i.e., entertainment, news, and learning).

Thus, Micro inﬂuencers can possess low reactions to their writings and low centrality

measures as shown in Figure 7;

Macro inﬂuencers: Their inﬂuence level lies between low and moderate inﬂuence. It

includes actors with important content, builders, or even trolls. They work on building

and growing their relationships and increasing their social network engagement

through creating interesting content or even inﬂammatory conversation. Thus, they

can possess high reactions to their writings as shown in Figure 7. They can become

mega inﬂuencers with time based on their ability to gain audience trust;

Mega Inﬂuencers: This category’s inﬂuence level can lie between moderate and high

inﬂuence levels. It may include business users, brokers, and newscasters. They are

followed by a large sector for being the source of information. Thus, they possess high

centrality measures as shown in Figure 7. They record an active presence on social

media, providing service, marketing, advertising, etc.;

A-list inﬂuencers or potential inﬂuencers: They own the highest inﬂuence level. They

are extremely popular and have between thousands and millions of followers. They

include: celebrities, the most recognizable people on earth that tend to act, sing, play

football, etc.; or professionals who have grown a strong brand for themselves for

sharing useful information about topics of professional interest, fostering interaction,

and being followed by many. Thus, they possess both high reactions and centrality

measures as shown in Figure 7.

4.3. Opinion Mining Process

This phase deals with the opinion texts of the data collected in the ﬁrst phase. It

includes two main steps: text preprocessing and opinion classiﬁcation. A lexicon technique

(i.e., TextBlob) is to be applied to the collected tweets. TextBlob is a natural language

processing (NLP) Python library that returns two values for SA: polarity and subjectivity,

with a standard range of

[−1.0, 1.0]

, where negative values refer to negative statements

and positive ones to positive statements. In our work, TextBlob was utilized for the two

mentioned steps of this phase. The reason for choosing a lexicon classiﬁer, TextBlob in

particular, is owing to the previous intention to perform a hybrid classiﬁcation of tweets by

combining lexicon, in this case, TextBlob, with ML, which is NL in the ﬁnal phase. TextBlob

Appl. Sci. 2022,12, 7697 12 of 20

was chosen for its proven ability to deal with informal texts from preprocessing to polarity

classiﬁcation [8]. The preprocessing step was performed using TextBlob and includes:

- The removal of the uniform resource locators (URLs), @username, stop words, etc.;

The substitution of slang, emoticons, etc. Example of one tweet before preprocessing:

RT @FIFAWorldCup: #FRA #FRA #FRA “This is amazing, it’s pinnacle: France are

on top of the world!” @FIFIAWorldCupFRA heard from #WorldCu. After prepro-

cessing, this tweet becomes: amazing pinnacle France top world heard. Afterward,

polarity classiﬁcation of the preprocessed tweet is performed using TextBlob. The

polarity classiﬁcation of the above-mentioned example is sentiment (polarity = 0.55,

subjectivity = 0.7).

4.4. Neutrosophic-Based OM Classiﬁcation

It is the ﬁnal and most important phase in this proposed model for two reasons: it

integrates the new elements of opinion into the traditional opinion elements. In addition,

NL can deal with different classiﬁcation uncertainties that do exist in the case of the OSNs:

Opinion dynamicity: Where opinions about the same entity can vary from one person

to the other. NL can deal with opinion dynamicity; its properties accept this difference

and can handle it to achieve a consensus opinion about the entity [

]. To achieve

consensus in neutrosophy, opinions with different observations (

polarity scores)

should have only one score of triple representation

(t,i,f)

. In this case, we implement

a weighted average formula for each

component inspired by the work performed

in [21] that is deﬁned as:

ts=ts1+1

2ts2+1

3ts3+. . . +1

ntsn

1+1

2+1

3+. . . +1

(5)

is=it1+1

2is2+1

3is3+. . . +1

nisn

1+1

2+1

3+. . . +1

(6)

fs=fs1+1

2fs+1

3fs3+. . . +1

nfsn

1+1

2+1

3+. . . +1

(7)

where

, and

are the overall true, indeterminate, and falsity scores of the opinion

text

, respectively.

and

represent the polarity scores assigned to the same

opinion sentence

by the observers of both the highest and the lowest inﬂuence

level

, respectively. For example,

ts1

is the true component of the opinion sentence

assigned by the ﬁrst highest inﬂuence observer.

Opinion indeterminacy: This is when humans cannot be certain. It is the case of

neither being true nor false. In the ﬁeld of OM, this can appear in classifying an

opinion as neutral for just being unable to determine its real intended polarity, or

for having positive and negative words of zero resultant sum, and thus, considered

neutral. This type of polarity classiﬁcation is not considered until NL appears; where

each opinion can have a degree of truth, indeterminacy, or falsity. NL can deal with

the failure in determining the polarity of text by considering it of a high indeterminate

degree, which is more accurate than considering it neutral or with any other wrong

polarity class that badly affects the accuracy of results.

Classiﬁcation ambiguity: It is a part of indeterminacy where the classiﬁed output

lies in the common area between two classes. NL can effectively deal with this case

by setting a conﬁdent value for the truth component (

). Figure 8shows an example

of a graphically represented neutrosophic set and how a conﬁdent value can be set

on it. Using this value, one can determine the signiﬁcance of

components for a

given opinion’s score. If

is greater than the conﬁdence value (i.e., 0.5 based on [

]),

Appl. Sci. 2022,12, 7697 13 of 20

then the corresponding

components can be considered insigniﬁcant [

]. All the

above-mentioned purposes can be achieved using the following steps:

i/f=insi gni f ic ant,t≥0.5

sig ni f ican t,t<0.5 (8)

Appl. Sci. 2022, 12, 7697 14 of 21

setting a confident value for the truth component (). Figure 8 shows an example of

a graphically represented neutrosophic set and how a confident value can be set on

it. Using this value, one can determine the significance of , components for a given

opinion’s score. If  is greater than the confidence value (i.e., 0.5 based on [9]), then

the corresponding , components can be considered insignificant [9]. All the

above-mentioned purposes can be achieved using the following steps:

/ = ,  ≥ 0.5

,  < 0.5

(8)

Figure 8. A confident value set on a neutrosophic set.

(1) Neutrosophication

In this step, the crisp inputs are converted to neutrosophic-based inputs using three

membership functions that represent: truth, indeterminate, and failure membership, per

input [20]:

 Input 1: Represents user’s influence (UI), the newly added opinion element. This in-

put ranged from 0 to 1 with three linguistic variables, low, moderate, and high influ-

ence (LI, MI, and HI), to build the truth, indeterminate, and falsity membership func-

tions. The membership functions are trapezoidal inspired by [10].

 Input 2: Represents the opinion orientation, the traditional opinion element, namely

polarity score (PS). This input’s range is [−1,1] with seven linguistic variables:

strong negative (SN), negative (NEG), weak negative (WN), neutral (N), weak posi-

tive (WP), positive (P), and strong positive (SP) with three triangular-shaped mem-

bership functions, also inspired by [10].

(2) Inference Engine/or Rule Evaluation

In this step, the neutrosophic inputs are converted into neutrosophic outputs using

IF-THEN rules. The rules were designed to cover all the truth, indeterminate, and falsity

cases for the inputs and their corresponding outputs. The above-mentioned inputs are the

antecedents joined by the minimum operator “AND”. The designed rules are based on

the designed rules in [9,10] and are found to be 45 rules. A sample of the designed NL

rules for the truth component () is listed in Table 1. MI-t, for example means true mod-

erate influence.

Figure 8. A conﬁdent value set on a neutrosophic set.

(1)

Neutrosophication

In this step, the crisp inputs are converted to neutrosophic-based inputs using three

membership functions that represent: truth, indeterminate, and failure membership,

per input [20]:

Input 1: Represents user ’s inﬂuence (UI), the newly added opinion element. This

input ranged from 0 to 1 with three linguistic variables, low, moderate, and high

inﬂuence (LI, MI, and HI), to build the truth, indeterminate, and falsity membership

functions. The membership functions are trapezoidal inspired by [10].

Input 2: Represents the opinion orientation, the traditional opinion element, namely

polarity score

(PS)

. This input’s range is

[−1, 1]

with seven linguistic variables:

strong negative (SN), negative (NEG), weak negative (WN), neutral (N), weak positive

(WP), positive (P), and strong positive (SP) with three triangular-shaped membership

functions, also inspired by [10].

(2)

Inference Engine/or Rule Evaluation

In this step, the neutrosophic inputs are converted into neutrosophic outputs using

IF-THEN rules. The rules were designed to cover all the truth, indeterminate, and falsity

cases for the inputs and their corresponding outputs. The above-mentioned inputs are

the antecedents joined by the minimum operator “AND”. The designed rules are based

on the designed rules in [

] and are found to be 45 rules. A sample of the designed

NL rules for the truth component

(t)

is listed in Table 1. MI-t, for example means true

moderate inﬂuence.

(3)

Deneutrosophication

In this ﬁnal NL step, the output of the inference engine (i.e., the neutrosophic outputs)

is converted into a crisp output using the corresponding three membership functions and

a suitable modulation technique. In this work, the center of gravity (COG) was chosen

to determine the defuzziﬁed output (

z∗

) from the accumulated output of the rules (

µc(z)

)

which is deﬁned as:

z∗=Zµc(z).zdz

µc(z)dz (9)

Appl. Sci. 2022,12, 7697 14 of 20

Table 1. Sample of the designed NL rules.

Rules # Rules

1 IF UI is ‘LI-t’ and PS is ‘SN-t’, THEN PS is ‘NEG-t’

2 IF UI is ‘LI-t’ and PS is ‘SP-t’, THEN PS is ‘P-t’

3 IF UI is ‘LI-t’ and PS is ‘NEG’, THEN PS is ‘WN-t’

4 IF UI is ‘LI-t’ and PS is ‘P-t’, THEN PS is ‘WP-t’

5 IF UI is ‘LI-t’ and PS is ‘WN-t’, THEN PS is ‘N-t’

6 IF UI is ‘LI-t’ and PS is ‘WP-t’, THEN PS is ‘N-t’

7 IF UI is ‘LI-t’ and PS is ‘N-t’, THEN PS is ‘N-t’

8 IF UI is ‘MI-t’ and PS is ‘N-t’, THEN PS is ‘N-t’

9 IF UI is ‘HI-t’ and PS is ‘N-t’, THEN PS is ‘N-t’

10 IF UI is ‘MI-t’ and PS is ‘SN-t’, THEN PS is ‘SN-t’

11 IF UI is ‘MI-t’ and PS is ‘NEG-t’, THEN PS is ‘NEG-t’

12 IF UI is ‘MI-t’ and PS is ‘WN-t’, THEN PS is ‘WN-t’

13 IF UI is ‘MI-t’ and PS is ‘WP-t’, THEN PS is ‘WP-t’

14 IF UI is ‘MI-t’ and PS is ‘P-t’, THEN PS is ‘P-t’

15 IF UI is ‘MI-t’ and PS is ‘SP-t’, THEN PS is ‘SP-t’

16 IF UI is ‘HI-t’ and PS is ‘SN-t’, THEN PS is ‘SN-t’

17 IF UI is ‘HI-t’ and PS is ‘SP-t’, THEN PS is ‘SP-t’

18 IF UI is ‘HI-t’ and PS is ‘NEG-t’, THEN PS is ‘SN-t’

19 IF UI is ‘HI-t’ and PS is ‘P-t’, THEN PS is ‘SP-t’

20 IF UI is ‘HI-t’ and PS is ‘WN-t’, THEN PS is ‘NEG-t’

21 IF UI is ‘HI-t’ and PS is ‘WP-t’, THEN PS is ‘P-t’

4.5. Desired Opinion Polarity Class

In this step, a ﬁnal polarity class is determined, inspired by the polarity classes applied

in [

]. This work applied seven polarity classes, known as: strong positive, positive, weak

positive, neutral/or indeterminate, weak negative, negative, and strong negative. Table 2

shows the seven polarity classes and their corresponding ranges. We added a new polarity

class to neutral, namely “indeterminate”. It is when the text is neither neutral nor any of

the existed classes. This is a bonus from using NL; we can say the class of a certain text is

undecided. The obtained ﬁnal class of polarity and the indeterminate class are determined

by Equation (8) as shown below:

Pol arity =truth component,t≥0.5

indeterminate,t<0.5 (10)

Table 2. The seven polarity levels [10].

Score Polarity

n>0.75 Strong Positive

0.25 <n≤0.75 Positive

0<n≤0.25 Weak Positive

0/NULL Neutral/undecided

−0.25 ≤n<0 Weak Negative

−0.75 ≤n<−0.25 Negative

n<−0.75 Strong Negative

5. Experimental Results

To effectively validate the proposed model, a desktop program was developed using

Python, for implementing TextBlob, and the matrix laboratory (MATLAB) libraries for

implementing ANN and NL. Toolboxes for ANN and fuzzy logic were used to build the

proposed ANN and NL classiﬁers. The fuzzy toolbox was used due to the unavailability of

a toolbox for NL until this time and the proven possibility of implementing NL using the

fuzzy toolbox as mentioned in [

]. The dataset already collected and ﬁltered in [

] was

used as a consequence of the absence of a benchmark dataset that combines the opinion

Appl. Sci. 2022,12, 7697 15 of 20

text, its writer’s following/followers list, and its tweet reaction counts. Table 3documents

the polarity classiﬁcation of 1080 collected tweets using TextBlob.

Table 3. Polarity distributions of the dataset using TextBlob.

Overall

Items

Polarity Classes and Distributions

Positive Neutral Negative

1080

559 (51.76%)

456 (42.22%)

65 (6.02%)

SP P WP SN NEG WN

150 232 177 1 32 32

Regarding the contribution phase of adding a new element into the basic opinion

elements, the constructed ANN operated with efﬁcient performance and attempted to

classify the opinion holders of the dataset into the four mentioned types. Table 4reports

the resultant ANN classiﬁcation errors of each of the opinion holder types. It was obvious

that the constructed ANN trained more on the low-level inﬂuencers than on the high-level

inﬂuencers. This can be due to the abundant presence of the low inﬂuencers in training

and real-life compared with the presence of the high inﬂuencers. Figure 9emphasizes this

observation and shows the results of the ANN classiﬁcation of the opinion holders in the

used dataset. The lower inﬂuencers have the highest percent, and this can be a caution

for the decisionmakers to not rely on the traditional OM results while dealing with OSNs

without classifying their opinion holders, as there would be spammers and people of low

impact whose opinions are not that worthwhile.

Table 4. Average errors in the ANN classiﬁcation.

Overall Items

Average Error in Opinion Holders ANN Classiﬁcation

Low Inﬂuence Moderate High Inﬂuence

1080

0.099 0.239 0.251

Micro Macro Mega A-Listers

0.089 0.234 0.248 0.208

Appl. Sci. 2022, 12, 7697 17 of 21

Figure 9. Opinion holders’ classification in the dataset.

According to our proposed model, opinion holders on OSNs share opinions of the

same polarity as others, but they should vary in their obtained OM polarity scores due to

their influence on the audience. Figure 10 shows the polarity change from a regular OM

process with its basic opinion elements using TextBlob and after integrating the new ele-

ment of opinion (i.e., user’s weight) into them using NL. It is obvious the difference in the

resultant polarity classes when considering users’ importance and influence on others. Due

to the large percentage of low influencers in the considered dataset, we can notice the in-

crease in the percentage of the neutral class for most texts due to the low effect of their users.

Figure 10. Polarity classes differences before and after considering user’s weight.

In the OM process, we usually use any tool/technique to obtain a polarity score for a

given text. Each tool may provide the same text a different polarity score due to many

factors such as the tool’s accuracy. In contrast, in our model, opinion holders can share

the same opinion text, but due to our consideration of a user’s weight, these same opinion

texts should have different polarity scores based on their sharer’s importance in the social

network. To deal with such a case is similar to dealing with applying different OM tech-

niques to the same text. In this case, the NL allows such a feature that it allows different

observations for the same text and can obtain a polarity score for the problem text. Table 5

shows an example sample of retweeted texts through different influence level users. They

were provided different scores and we reported how the NL dealt with such cases.

Figure 9. Opinion holders’ classiﬁcation in the dataset.

Appl. Sci. 2022,12, 7697 16 of 20

According to our proposed model, opinion holders on OSNs share opinions of the

same polarity as others, but they should vary in their obtained OM polarity scores due

to their inﬂuence on the audience. Figure 10 shows the polarity change from a regular

OM process with its basic opinion elements using TextBlob and after integrating the new

element of opinion (i.e., user’s weight) into them using NL. It is obvious the difference in

the resultant polarity classes when considering users’ importance and inﬂuence on others.

Due to the large percentage of low inﬂuencers in the considered dataset, we can notice

the increase in the percentage of the neutral class for most texts due to the low effect of

their users.