SENTIMART: A Web-Based Ordering, Inventory, and Feedback System based on Long Short-Term Memory

(LSTM)-based Sentiment Analysis on RTEA Shop is a one-stop web-based system that was created to help

manage operational drawbacks in the field of specialty tea retail. The main innovation of it is that it applies the

LSTM-based sentiment analysis algorithm to customer feedback to produce predictive analysis of the feedback,

used to forecast the inventory and customized advice on which products to purchase. Constructed using PHP-

Technical respondents expressed confidence in the system's sound architecture and the precision of its LSTM

sentiment analysis engine, giving it excellent grades for functionality and reliability. Although it was still given

a high rating, portability scored somewhat lower, indicating a small opportunity for future improvement in terms

of cross-platform consistency.

This paper Sentimart: A Web-Based Ordering, Inventory & Feedback System using Long Short-Term Memory

(LSTM)-Based Sentiment Analysis for RTEA Shop” is a developmental type of technology research that aims

to design, develop, and evaluate a web-based system guided by the ISO/IEC 25010 software quality model

focusing on functionality, reliability, efficiency, usability, and portability. The development follows the

Waterfall Model, which involves sequential phases such as requirements analysis, system design,

implementation, testing, deployment, and maintenance to ensure systematic progress and quality assurance. Data

The study concludes that SENTIMART is a reliable, efficient, and easy-to-use solution that can improve

specialized tea stores' customer-facing services as well as their operational structure. The researchers suggest

additional improvements based on the evaluation results and project constraints. These include including more

input channels like speech and emoji analysis, putting OTP verification into place for enhanced security, and

refining the server infrastructure and LSTM model to get rid of any possible real-time processing delays under

heavy traffic. Furthermore, it is recommended to conduct a continuous trial to more accurately evaluate the

ystem's long-term impact on sales and customer loyalty, ensuring its scalability and sustaining success in the

competitive food and beverage industry.

paper-based inventory management, which frequently cause shortages of stock, surplus, and inaccurate

predictions. Such inefficiencies decrease productivity and customer satisfaction, which manifests the necessity

of the digital solutions, which would automatize inventory tracking and enhance the service reliability.

Ferrara (2011) stressed that the intelligent systems should also be designed with adaptive cognitive functions

that could deliver appropriate responses to the varying retail environment. The Long Short-Term Memory

(LSTM) models of machine learning can provide this flexibility through the interpretation of textual responses

and the detection of emotional habits in customer input. The article by Hossain et al. (2020) revealed that

sentiment analysis using LSTM can be highly accurate in identifying the emotional tone and intent, which may

be used as an element of a customer-driven decision support system in retail and service industries.

Efficient inventory management is still one of the pillars of sustainable retail. According to Smith and Johnson

The other crucial element of competitiveness in the beverage sector is customer experience (CX). Lemon and

Verhoeff (2016) claimed that the improvement of CX leads to a stronger customer loyalty with the help of

personalized and consistent service interactions. Tolentino (2022) has also found that quality of products,

effective service and online interaction are major factors that determine consumer satisfaction and brand loyalty

among the milk tea customers in Taguig City. To this end, Elnagar, Khalifa, and Einea (2020) confirmed that

hybrid artificial intelligence models, which are CNN and RNN architectures, are more accurate in sentiment

The COVID19 pandemic boosted the transition to digital forms meaning that small businesses had to adjust

online systems to survive. According to Jribi et al. (2020), digital ordering and delivery platforms proved to be

the necessary means of continuity and fulfilling ever-changing customer expectations. This change highlights

The study aims to develop A Web-based Ordering, Inventory, & Feedback System using Long Short-Term

Memory (LSTM) - Based Sentiment Analysis for RTEA Shop. The specific objectives are:

Develop feedback platform with LSTM sentiment analysis: Build a system to gather feedback (social media,

surveys, reviews) and classify sentiment (positive/neutral/negative) using an LSTM algorithm.

Automate inventory & personalize recommendations using sentiment: Use sentiment-derived insights to forecast

demand (automating inventory/restocking) and generate tailored product recommendations.

Evaluate impact & ensure ISO 25010 compliance: Measure the system's effect on operational efficiency/service

quality (via reports/user feedback) while ensuring compliance with ISO/IEC 25010 standards.

Implement role-based access control: Define and implement access-specific modules/interfaces for admin, staff,

and customer roles.

The main goal of this project is to set up and execute a data-driven system for RTEA that enhances customer

waiting during busy times.

Inventory Monitoring: Provides real-time tracking of raw supplies, such as milk and tea leaves. To avoid stock-

outs or overstocking, the system forecasts demand and notifies employees of usage.

Consumer feedback system: Classifies consumer comments from surveys, social media, and mobile apps as

neutral, negative, or positive using LSTM-based sentiment analysis. Management decisions are guided by

insights.

Report Generation & Dashboard: Offers administrators automated reports on inventory, sales, and feedback via

an intuitive dashboard for decision-making.

Multi-User Roles: Provides role-specific access and functionality to admin, staff, and customer accounts.

Quality Standard: To guarantee functionality, dependability, usefulness, and efficiency, ISO/IEC 25010

system's immediate applicability to other industries without substantial change is limited by its industry-specific

design for specialty tea sale. The lack of OTP verification compromises security and may lead to user

authentication issues. Additionally, the cloud-based architecture requires current devices and reliable internet

access, which may limit accessibility in places with unreliable networks. These restrictions point to important

The following theories, conceptions, ideas, and presumptions form the theoretical basis for comprehending this

research inquiry:

Sentimart's core intelligence relies on LSTM (Long Short-Term Memory) networks to identify customer emotion

through text. The results of this analysis are not only reported, but also actively used by recommendation

of a given stock. The primary and crucial task at the core of the text analysis is the use of preprocessing libraries

to clean and support feedback information. These algorithms form a model in which customer commentary

Just-in-Time (JIT) inventory theory is the foundation of Sentimart's stock management strategy (Smith &

Customer Experience: The Customer Experience (CX) hypothesis ensures that the system boosts loyalty, claim

Lemon and Verhoef (2016). Sentimart's recommendation system customizes products (for example,

recommending "lychee jelly" to fans of oolong tea) in accordance with Tolentino's (2022) study on Filipino

consumer preferences. Sentimart also detects emotional cues to start service recovery, such as annoyance in

"Waisted 30 minutes!"

Figure 1: Input-Process-Output Model

The Input Assume that active listening and observation are the first steps in this system. It draws in real-world

customer voices, including reviews, grievances, and general feedback to understand their feelings and

experiences. At the same time, it uses the company's internal pulse to collect operational data, including sales

The Process Technology analyzes client feedback in-depth using an AI model (LSTM), identifying feelings like

connection between what customers believe and what is happening on the job site, such as declining sales or

stock outs, which empowers them to make wise decisions. Smarter data in terms of "Ordering" selections and

customer trust, the study emphasizes the necessity of technology like smart ordering and inventory management.

Implementation (coding), Testing (validation), Deployment (go-live), and Maintenance (updates/bug patches)

experience, these users also examined it from a practical standpoint, looking at things like ordering, providing

feedback, and managing accounts.

Ten (10) experts in the computer industry who specialize in web development, database administration, or

machine learning make up the technical respondents. These experts evaluated the technical aspects of the system,

By offering an unbiased way to evaluate respondents’ comments, this rating system made sure that the