Prioritized Text Detergent: Comparing Two Judgment Scales of Analytic Hierarchy Process on Prioritizing Pre-Processing Techniques on Social Media Sentiment Analysis

Most companies use social media data for business. Sentiment analysis automatically gathers analyses and summarizes this type of data. Managing unstructured social media data is difficult. Noisy data is a challenge to sentiment analysis. Since over 50% of the sentiment analysis process is data pre-...

Full description

Saved in:
Bibliographic Details
Main Authors: Ummu Hani’ Hair Zaki, Roliana Ibrahim, Shahliza Abd Halim, Izyan Izzati Kamsani
Format: Article
Language:English
Published: University of Baghdad, College of Science for Women 2024-02-01
Series:مجلة بغداد للعلوم
Subjects:
Online Access:https://bsj.uobaghdad.edu.iq/index.php/BSJ/article/view/9750
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850064266210574336
author Ummu Hani’ Hair Zaki
Roliana Ibrahim
Shahliza Abd Halim
Izyan Izzati Kamsani
author_facet Ummu Hani’ Hair Zaki
Roliana Ibrahim
Shahliza Abd Halim
Izyan Izzati Kamsani
author_sort Ummu Hani’ Hair Zaki
collection DOAJ
description Most companies use social media data for business. Sentiment analysis automatically gathers analyses and summarizes this type of data. Managing unstructured social media data is difficult. Noisy data is a challenge to sentiment analysis. Since over 50% of the sentiment analysis process is data pre-processing, processing big social media data is challenging too. If pre-processing is carried out correctly, data accuracy may improve. Also, sentiment analysis workflow is highly dependent. Because no pre-processing technique works well in all situations or with all data sources, choosing the most important ones is crucial. Prioritization is an excellent technique for choosing the most important ones. As one of many Multi-Criteria Decision Making (MCDM) methods, the Analytic Hierarchy Process (AHP) is preferred for handling complicated decision-making challenges using several criteria. The Consistency Ratio (CR) scores were used to examine pair-wise comparisons to evaluate the AHP. This study used two judgment scales to get the most consistent judgment. Firstly, the Saaty judgment scale (SS), then the Generalized Balanced Scale (GBS). It investigated whether two different AHP judgment scales would affect decision-making. The main criteria for prioritizing pre-processing techniques in sentiment analysis are Punctuation, Spelling, Number, and Context. These four criteria also contain sub-criteria. GBS pair-wise comparisons are closer to the CR value than SS, reducing the alternatives’ weight ratios. This paper explains how AHP aids logical decision-making. Prioritizing pre-processing techniques with AHP can be a paradigm for other sentiment analysis stages. In short, this paper adds another contribution to the Big Data Analytics domain.
format Article
id doaj-art-fe15e2c8d5c743059209f205ccd5e499
institution DOAJ
issn 2078-8665
2411-7986
language English
publishDate 2024-02-01
publisher University of Baghdad, College of Science for Women
record_format Article
series مجلة بغداد للعلوم
spelling doaj-art-fe15e2c8d5c743059209f205ccd5e4992025-08-20T02:49:20ZengUniversity of Baghdad, College of Science for Womenمجلة بغداد للعلوم2078-86652411-79862024-02-01212(SI)10.21123/bsj.2024.9750Prioritized Text Detergent: Comparing Two Judgment Scales of Analytic Hierarchy Process on Prioritizing Pre-Processing Techniques on Social Media Sentiment Analysis Ummu Hani’ Hair Zaki0Roliana Ibrahim1Shahliza Abd Halim2Izyan Izzati Kamsani3Department of Applied Computing, Faculty of Computing, Universiti Teknologi Malaysia, Johor Bahru, Johor, Malaysia.Department of Applied Computing, Faculty of Computing, Universiti Teknologi Malaysia, Johor Bahru, Johor, Malaysia.Department of Software Engineering, Faculty of Computing, Universiti Teknologi Malaysia, Johor Bahru, Johor, Malaysia.Department of Applied Computing, Faculty of Computing, Universiti Teknologi Malaysia, Johor Bahru, Johor, Malaysia. Most companies use social media data for business. Sentiment analysis automatically gathers analyses and summarizes this type of data. Managing unstructured social media data is difficult. Noisy data is a challenge to sentiment analysis. Since over 50% of the sentiment analysis process is data pre-processing, processing big social media data is challenging too. If pre-processing is carried out correctly, data accuracy may improve. Also, sentiment analysis workflow is highly dependent. Because no pre-processing technique works well in all situations or with all data sources, choosing the most important ones is crucial. Prioritization is an excellent technique for choosing the most important ones. As one of many Multi-Criteria Decision Making (MCDM) methods, the Analytic Hierarchy Process (AHP) is preferred for handling complicated decision-making challenges using several criteria. The Consistency Ratio (CR) scores were used to examine pair-wise comparisons to evaluate the AHP. This study used two judgment scales to get the most consistent judgment. Firstly, the Saaty judgment scale (SS), then the Generalized Balanced Scale (GBS). It investigated whether two different AHP judgment scales would affect decision-making. The main criteria for prioritizing pre-processing techniques in sentiment analysis are Punctuation, Spelling, Number, and Context. These four criteria also contain sub-criteria. GBS pair-wise comparisons are closer to the CR value than SS, reducing the alternatives’ weight ratios. This paper explains how AHP aids logical decision-making. Prioritizing pre-processing techniques with AHP can be a paradigm for other sentiment analysis stages. In short, this paper adds another contribution to the Big Data Analytics domain. https://bsj.uobaghdad.edu.iq/index.php/BSJ/article/view/9750Analytical Hierarchy Process, Data Pre-processing, Multi-Criteria Decision-Making, Pre-processing Technique, Prioritization, Sentiment Analysis, Social Media
spellingShingle Ummu Hani’ Hair Zaki
Roliana Ibrahim
Shahliza Abd Halim
Izyan Izzati Kamsani
Prioritized Text Detergent: Comparing Two Judgment Scales of Analytic Hierarchy Process on Prioritizing Pre-Processing Techniques on Social Media Sentiment Analysis
مجلة بغداد للعلوم
Analytical Hierarchy Process, Data Pre-processing, Multi-Criteria Decision-Making, Pre-processing Technique, Prioritization, Sentiment Analysis, Social Media
title Prioritized Text Detergent: Comparing Two Judgment Scales of Analytic Hierarchy Process on Prioritizing Pre-Processing Techniques on Social Media Sentiment Analysis
title_full Prioritized Text Detergent: Comparing Two Judgment Scales of Analytic Hierarchy Process on Prioritizing Pre-Processing Techniques on Social Media Sentiment Analysis
title_fullStr Prioritized Text Detergent: Comparing Two Judgment Scales of Analytic Hierarchy Process on Prioritizing Pre-Processing Techniques on Social Media Sentiment Analysis
title_full_unstemmed Prioritized Text Detergent: Comparing Two Judgment Scales of Analytic Hierarchy Process on Prioritizing Pre-Processing Techniques on Social Media Sentiment Analysis
title_short Prioritized Text Detergent: Comparing Two Judgment Scales of Analytic Hierarchy Process on Prioritizing Pre-Processing Techniques on Social Media Sentiment Analysis
title_sort prioritized text detergent comparing two judgment scales of analytic hierarchy process on prioritizing pre processing techniques on social media sentiment analysis
topic Analytical Hierarchy Process, Data Pre-processing, Multi-Criteria Decision-Making, Pre-processing Technique, Prioritization, Sentiment Analysis, Social Media
url https://bsj.uobaghdad.edu.iq/index.php/BSJ/article/view/9750
work_keys_str_mv AT ummuhanihairzaki prioritizedtextdetergentcomparingtwojudgmentscalesofanalytichierarchyprocessonprioritizingpreprocessingtechniquesonsocialmediasentimentanalysis
AT rolianaibrahim prioritizedtextdetergentcomparingtwojudgmentscalesofanalytichierarchyprocessonprioritizingpreprocessingtechniquesonsocialmediasentimentanalysis
AT shahlizaabdhalim prioritizedtextdetergentcomparingtwojudgmentscalesofanalytichierarchyprocessonprioritizingpreprocessingtechniquesonsocialmediasentimentanalysis
AT izyanizzatikamsani prioritizedtextdetergentcomparingtwojudgmentscalesofanalytichierarchyprocessonprioritizingpreprocessingtechniquesonsocialmediasentimentanalysis