A multi-task dual attention deep recommendation model using ratings and review helpfulness

Liu, Zhen; Yuan, Bin; Ma, Ying

doi:10.1007/s10489-021-02666-y

Cited by 16 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used both task-specific and pretrained embeddings (Word2vec here) to intuitively determine which method was more effective with our dataset. Consistent with earlier work (Chang et al, 2020; Jain et al, 2022; Liu et al, 2022), each distinct word in the corpus was mapped onto a 300-dimension vector to obtain a word-embedding representation.…”

Section: Methodsmentioning

confidence: 99%

A Predictive Model Based on TripAdvisor Textual Reviews: Early Destination Recommendations for Travel Planning

Zhang,

Tan,

Jiao

et al. 2024

Sage Open

View full text Add to dashboard Cite

Although many studies have considered the effects of online reviews on tourists’ decisions, none have directly investigated how to leverage open data analyses to create early choice sets and facilitate destination planning. This paper illustrates how salient characteristics can be mined from the shared experiences embedded in review data and incorporated into a predictive model to build a travel counseling approach. The model is designed by first defining a prediction-based mechanism from online reviews and then generating a multinomial classification problem on all candidate destinations of interest. The model is implemented by applying Natural Language Processing (NLP) and Deep Learning (DL) technologies to review textual features. The model is validated using 75,315 reviews from TripAdvisor along with destinations from 257 U.S. national parks. Empirical results indicate a best classification accuracy of 67%, outperforming two previous approaches. Findings shed light on how to exploit past tourists’ experiences to generate early destination recommendations to identify items for choice sets and reduce tourists’ travel-planning effort. Theoretical and managerial implications regarding social media analytics are provided based on online review meta-data in touristic management.

show abstract

Section: Methodsmentioning

confidence: 99%

A Predictive Model Based on TripAdvisor Textual Reviews: Early Destination Recommendations for Travel Planning

Zhang,

Tan,

Jiao

et al. 2024

Sage Open

View full text Add to dashboard Cite

show abstract

“…For instance, the Attention-based techniques (TCC12) have also gained popularity in recommendation systems. Liu et al [308] proposed the DARMH model, integrating sentiment analysis (TCF02), attention-based (TCC12), convolution neural network (TCC07), and multi-layer (TCC11) techniques. Da'u et al [314] proposed the MDRR model, incorporating rate prediction (TCA05), collaborative filtering (TCC01), and attention-based (TCC12) techniques.…”

Section: ) Technique Diversity and Integrationmentioning

confidence: 99%

Deep Learning-Based Recommendation System: Systematic Review and Classification

Li,

Ishak,

Ibrahim

et al. 2023

IEEE Access

View full text Add to dashboard Cite

In recent years, recommendation systems have become essential for businesses to enhance customer satisfaction and generate revenue in various domains, such as e-commerce and entertainment. Deep learning techniques have significantly improved the accuracy and efficiency of these systems. However, there is a lack of literature on classification in systematic review papers that summarize the latest deep-learning techniques used in recommendation systems. Moreover, certain existing review papers have either overlooked state-of-the-art techniques or restricted their coverage to a narrow spectrum of domains.To address these research gaps, we present a systematic review paper that comprehensively analyzes the literature on deep learning techniques in recommendation systems, specifically using term classification. We analyzed relevant studies published between 2018 and February 2023, examining the techniques, datasets, domains, and measurement metrics used in these studies, utilizing a thorough SLR strategy. Our review reveals that deep learning techniques, such as graph neural networks, convolutional neural networks, and recurrent neural networks, have been widely used in recommendation systems. Furthermore, our study highlights the emerging area of research in domain classification, which has shown promising results in applying deep learning techniques to domains such as social networks, e-commerce, and e-learning. Our review paper offers insights into the deep learning techniques used across different recommendation systems and provides suggestions for future research. Our review fills a critical research gap and offers a valuable resource for researchers and practitioners interested in deep learning techniques for recommendation systems. INDEX TERMSDeep learning, term classification, recommendation system, systematic review, state-ofthe-art techniques I. INTRODUCTION

show abstract

“…In a similar work, Liu et al (2022) proposed a multi-task Dual Attention Recommendation Model (DARMH) for both review helpfulness and rating prediction. This work utilized word embeddings and user ID embeddings from a specific Amazon dataset.…”

Section: Related Workmentioning

confidence: 99%

Multi-task Ensemble Learning for Fake Reviews Detection and Helpfulness Prediction: A Novel Approach

Melleng,

Loughrey,

2023

Proceedings of the Conference Recent Advances in Natural Language Processing - Large Language Models for Natural Language Proce

View full text Add to dashboard Cite

Research on fake reviews detection and review helpfulness prediction is prevalent, yet most studies tend to focus solely on either fake reviews detection or review helpfulness prediction, considering them separate research tasks. In contrast to this prevailing pattern, we address both challenges concurrently by employing a multi-task learning approach. We posit that undertaking these tasks simultaneously can enhance the performance of each task through shared information among features. We utilize pre-trained RoBERTa embeddings with a document-level data representation. This is coupled with an array of deep learning and neural network models, including Bi-LSTM, LSTM, GRU, and CNN. Additionally, we employ ensemble learning techniques to integrate these models, with the objective of enhancing overall prediction accuracy and mitigating the risk of overfitting. The findings of this study offer valuable insights to the fields of NLP and machine learning and present a novel perspective on leveraging multi-task learning for the twin challenges of fake reviews detection and review helpfulness prediction.

show abstract

A multi-task dual attention deep recommendation model using ratings and review helpfulness

Cited by 16 publications

References 24 publications

A Predictive Model Based on TripAdvisor Textual Reviews: Early Destination Recommendations for Travel Planning

A Predictive Model Based on TripAdvisor Textual Reviews: Early Destination Recommendations for Travel Planning

Deep Learning-Based Recommendation System: Systematic Review and Classification

Multi-task Ensemble Learning for Fake Reviews Detection and Helpfulness Prediction: A Novel Approach

Contact Info

Product

Resources

About