Melola Discovery

← Melola Discovery

Journal SINTA 1

Enhancing Recommendation Systems via Aspect-Level Sentiment Analysis for Identifying Unreliable Reviews

Indonesian Journal of Electical Engineering and Informatics (IJEEI) · Vol. 14 No. 2 (2026) · pp. 435–445

DOI
10.52549/ijeei.v14i2.7834
ISSN
2089-3272, 2089-3272
Published
2026-04-19
Publisher
IAES Indonesian Section
Language
en

Abstract

User-generated reviews are an important source of information for e-commerce recommendation systems. However, reviews may contain conflicting opinions across product aspects such as quality, price, and delivery, which can weaken both review-level trust and aspect-level signals. To address this issue, we propose AspectGuard, a filtering framework based on Aspect-Based Sentiment Analysis (ABSA) and a Sentiment Divergence Score (SDS) that quantifies disagreement across aspect-level sentiments within a review. Reviews with high divergence are identified as potentially unreliable and excluded before constructing recommendation profiles. To isolate the contribution of the proposed filtering mechanism, we compare the same content-based recommendation model with and without AspectGuard filtering. Experiments conducted on a subset of the Amazon Reviews 2023 Electronics dataset show that the proposed filtering strategy improves both rating prediction and ranking quality. These results indicate that aspect level sentiment divergence can serve as an effective signal for identifying unreliable reviews and improving the reliability of recommendation systems.

Keywords

Collaboration network of the authors

10 authors · 25 co-authorship links

Hover or tap a name to highlight its co-authors. Double-click to open the author's page.

  • University of Hassan II Casablanca
  • Affiliation unknown
  • Different organisations
  • Same organisation
  • Affiliation unknown
  • Thicker line = more joint articles · bigger circle = more articles
Show as table
Co-authorOrganisationJoint articles
Saïd NouhUniversity of Hassan II Casablanca1
Bouchaib AylajAffiliation unknown1
Mohammed El AssadAffiliation unknown1
Imrane Chemseddine IdrissiAffiliation unknown1
Seddiq El Kasmi AlaouiAffiliation unknown1

Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.

Metadata source: OAI-PMH (metadata jurnal) http://section.iaesonline.com/index.php/IJEEI/oai, first harvested 8 Nov 2026, last seen 8 Nov 2026.
Original metadata (oai_dc) 
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en">Enhancing Recommendation Systems via Aspect-Level Sentiment Analysis for Identifying Unreliable Reviews</dc:title>
	<dc:creator xml:lang="en">Lghaouch, El Mehdi</dc:creator>
	<dc:creator xml:lang="en">Abbour, Fatima Zahra</dc:creator>
	<dc:creator xml:lang="en">Ounacer, Soumaya</dc:creator>
	<dc:creator xml:lang="en">Ardchir, Soufiane</dc:creator>
	<dc:creator xml:lang="en">Azzouazi, Mohamed</dc:creator>
	<dc:subject xml:lang="en">Artificial Intelligence</dc:subject>
	<dc:subject xml:lang="en">Sentiment Analysis</dc:subject>
	<dc:subject xml:lang="en">Review Filtering</dc:subject>
	<dc:subject xml:lang="en">Recommendation Systems</dc:subject>
	<dc:subject xml:lang="en">Aspect Analysis</dc:subject>
	<dc:subject xml:lang="en">E-Commerce Reviews</dc:subject>
	<dc:description xml:lang="en">User-generated reviews are an important source of information for e-commerce recommendation systems. However, reviews may contain conflicting opinions across product aspects such as quality, price, and delivery, which can weaken both review-level trust and aspect-level signals. To address this issue, we propose AspectGuard, a filtering framework based on Aspect-Based Sentiment Analysis (ABSA) and a Sentiment Divergence Score (SDS) that quantifies disagreement across aspect-level sentiments within a review. Reviews with high divergence are identified as potentially unreliable and excluded before constructing recommendation profiles. To isolate the contribution of the proposed filtering mechanism, we compare the same content-based recommendation model with and without AspectGuard filtering. Experiments conducted on a subset of the Amazon Reviews 2023 Electronics dataset show that the proposed filtering strategy improves both rating prediction and ranking quality. These results indicate that aspect level sentiment divergence can serve as an effective signal for identifying unreliable reviews and improving the reliability of recommendation systems.</dc:description>
	<dc:publisher xml:lang="en">IAES Indonesian Section</dc:publisher>
	<dc:date>2026-04-19</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://section.iaesonline.com/index.php/IJEEI/article/view/7834</dc:identifier>
	<dc:identifier>10.52549/ijeei.v14i2.7834</dc:identifier>
	<dc:source xml:lang="en">Indonesian Journal of Electrical Engineering and Informatics (IJEEI); Vol. 14 No. 2: June 2026; 435-445</dc:source>
	<dc:source>2089-3272</dc:source>
	<dc:source>2089-3272</dc:source>
	<dc:language>en</dc:language>
	<dc:relation>https://section.iaesonline.com/index.php/IJEEI/article/view/7834/1080</dc:relation>
</oai_dc:dc>