An MDSS Architecture for Customer Experience Decision Support in E-Commerce Using Data-Driven Decision-Making

Direct product reviews on e-commerce platforms provide information about consumer experiences, but their use in marketing decisions requires connecting heterogeneous inputs, aspect-level analysis, and interpretable outputs. This study proposes a conceptual marketing decision support system (MDSS) architecture grounded in a systematic literature review reported with support from the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines. The research adopts a descriptive and analytical documentary approach that connects published evidence with architectural decisions. The synthesis includes 28 studies and examines data management, opinion analysis, indicator construction, and assisted interpretation in relation to decision support. The resulting architecture organizes automated daily acquisition, input normalization and validation, aspect-based sentiment analysis, polarity aggregation in Python, and interactive querying through a large language model (LLM). A common JSON model accommodates platform connectors and exported files, while validation states determine which records proceed to analysis. Valid aspect mentions retain their product and review identifiers and supporting textual evidence. Mean polarity summarizes classifications encoded as negative, neutral, and positive, together with the number of valid mentions. The LLM layer uses predefined Python tools to query aspects, compare products or publication periods, and retrieve evidence. Its principal output is a decision-oriented report connecting findings, supporting evidence, marketing implications, possible actions, and information still needed for assessment. An application programming interface exposes queries, reports, and processing status. The contribution is an architectural specification that connects consumer opinions with interpretable decision support while preserving human judgment. Data-driven decision-making guides the link between findings and evidence, and Marketing 7.0 provides a conceptual context for consumer understanding and human interpretation. Subsequent development would examine processing quality, reporting fidelity, integration, and resource consumption.

Authors

Publication Details

Journal
International Journal of Research and Innovation in Social Science
Published
2026-11-14
DOI
https://doi.org/10.47772/ijriss.2026.102500012
Primary Topic
Sentiment Analysis and Opinion Mining
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

An MDSS Architecture for Customer Experience Decision Support in E-Commerce Using Data-Driven Decision-Making

Luis Alejandro Santana Valadez, Tania Ofelia López Zerón, Adrián Sánchez Ortega, Marcelo Quezada Quiterio et al.
International Journal of Research and Innovation in Social Science
Sentiment Analysis and Opinion Mining
article

An MDSS Architecture for Customer Experience Decision Support in E-Commerce Using Data-Driven Decision-Making

Luis Alejandro Santana Valadez, Tania Ofelia López Zerón, Adrián Sánchez Ortega, Marcelo Quezada Quiterio, Arizbeth Escudero Hernández, Efraín Mohedano Torres
article en

Abstract

Direct product reviews on e-commerce platforms provide information about consumer experiences, but their use in marketing decisions requires connecting heterogeneous inputs, aspect-level analysis, and interpretable outputs. This study proposes a conceptual marketing decision support system (MDSS) architecture grounded in a systematic literature review reported with support from the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines. The research adopts a descriptive and analytical documentary approach that connects published evidence with architectural decisions. The synthesis includes 28 studies and examines data management, opinion analysis, indicator construction, and assisted interpretation in relation to decision support. The resulting architecture organizes automated daily acquisition, input normalization and validation, aspect-based sentiment analysis, polarity aggregation in Python, and interactive querying through a large language model (LLM). A common JSON model accommodates platform connectors and exported files, while validation states determine which records proceed to analysis. Valid aspect mentions retain their product and review identifiers and supporting textual evidence. Mean polarity summarizes classifications encoded as negative, neutral, and positive, together with the number of valid mentions. The LLM layer uses predefined Python tools to query aspects, compare products or publication periods, and retrieve evidence. Its principal output is a decision-oriented report connecting findings, supporting evidence, marketing implications, possible actions, and information still needed for assessment. An application programming interface exposes queries, reports, and processing status. The contribution is an architectural specification that connects consumer opinions with interpretable decision support while preserving human judgment. Data-driven decision-making guides the link between findings and evidence, and Marketing 7.0 provides a conceptual context for consumer understanding and human interpretation. Subsequent development would examine processing quality, reporting fidelity, integration, and resource consumption.

International Journal of Research and Innovation in Social ScienceVol. 10(25)
Sentiment Analysis and Opinion Mining
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon