Sentiment Analysis to Support Marketing Decision Making Process: A Hybrid Model

Marshan, Alaa; Kansouzidou, Georgia; Ioannou, Athina

doi:10.1007/978-3-030-63089-8_40

Cited by 5 publications

(2 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CRISP-DM is a widely used, structured approach for data mining projects, encompassing six key stages: business understanding, data understanding, data preparation, modeling, evaluation, and deployment (Marbán et al, 2009 ). This methodology has been successfully applied in various domains, including healthcare (Martínez-Plumed et al, 2021 ; Marshan et al, 2021 ).…”

Section: Methodsmentioning

confidence: 99%

MedT5SQL: a transformers-based large language model for text-to-SQL conversion in the healthcare domain

Marshan,

Almutairi,

Ioannou

et al. 2024

Front. Big Data

Self Cite

View full text Add to dashboard Cite

IntroductionIn response to the increasing prevalence of electronic medical records (EMRs) stored in databases, healthcare staff are encountering difficulties retrieving these records due to their limited technical expertise in database operations. As these records are crucial for delivering appropriate medical care, there is a need for an accessible method for healthcare staff to access EMRs.MethodsTo address this, natural language processing (NLP) for Text-to-SQL has emerged as a solution, enabling non-technical users to generate SQL queries using natural language text. This research assesses existing work on Text-to-SQL conversion and proposes the MedT5SQL model specifically designed for EMR retrieval. The proposed model utilizes the Text-to-Text Transfer Transformer (T5) model, a Large Language Model (LLM) commonly used in various text-based NLP tasks. The model is fine-tuned on the MIMICSQL dataset, the first Text-to-SQL dataset for the healthcare domain. Performance evaluation involves benchmarking the MedT5SQL model on two optimizers, varying numbers of training epochs, and using two datasets, MIMICSQL and WikiSQL.ResultsFor MIMICSQL dataset, the model demonstrates considerable effectiveness in generating question-SQL pairs achieving accuracy of 80.63%, 98.937%, and 90% for exact match accuracy matrix, approximate string-matching, and manual evaluation, respectively. When testing the performance of the model on WikiSQL dataset, the model demonstrates efficiency in generating SQL queries, with an accuracy of 44.2% on WikiSQL and 94.26% for approximate string-matching.DiscussionResults indicate improved performance with increased training epochs. This work highlights the potential of fine-tuned T5 model to convert medical-related questions written in natural language to Structured Query Language (SQL) in healthcare domain, providing a foundation for future research in this area.

show abstract

Section: Methodsmentioning

confidence: 99%

MedT5SQL: a transformers-based large language model for text-to-SQL conversion in the healthcare domain

Marshan,

Almutairi,

Ioannou

et al. 2024

Front. Big Data

Self Cite

View full text Add to dashboard Cite

show abstract

“…Therefore, it is used to track opinions, judgments, and beliefs expressed in reviews, blogs, tweets, comments, and social networking sites toward a product, a service, issues, events, a person, and so on [3]. Nowadays, many customers make use of this feedback for their decisionmaking [4]. Most inquiries have concentrated on English SA, but few have tended to Arabic SA [5].…”

Section: Introductionmentioning

confidence: 99%

Arabic Language Sentiment Analysis using Bidirectional Long Short Term Memory

Elsamadony

Keshk²,

abdelatey³

2022

IJCI. International Journal of Computers and Information

View full text Add to dashboard Cite

The amount of data generated in the digital era is huge since the super growth of social networks. Sentiment analysis (SA) seeks to extract opinions from a text and determine the polarity (positive, negative, or neutral). SA is widely used to refer to English. The topic of this study is SA in the Arabic language. There is an amalgamation between Word2Vec and Bidirectional Long-Short Time Memory (BLSTM) used in this paper. Firstly, words in reviews are transferred into their corresponding vectors with word representation models. Secondly, the sequence of words in the sentences passes as input to BLSTM. BLSTM not only captures long-range information and solves the gradient attenuation problem, but it also better represents the future semantics of the word sequence. The polarity was calculated using Word2Vec representation models, which rely on meaning and context. A BLSTM-based deep learning (DL) architecture is proposed. The result shows that the BLSTM Model Architecture surpasses ML, CNN, and LSTM Architectures with a maximum accuracy of 94.88 percent.

show abstract