# Gradient-Boosted Decision Tree for Listwise Context Model in Multimodal Review Helpfulness Prediction

arXiv: https://arxiv.org/abs/2305.12678 · HTML: https://mlsanity.com/paper/2305.12678/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 35 references that are in the map.
- First posted on arXiv 22 May 2023.

## Builds on (most cited first, 15 of 15)

- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Bilateral Multi-Perspective Matching for Natural Language Sentences](https://mlsanity.com/paper/1702.03814/) (2017)
- [Contrastive Learning for Neural Topic Model](https://mlsanity.com/paper/2110.12764/) (2021)
- [NeuralNDCG: Direct Optimisation of a Ranking Metric via Differentiable Relaxation of Sorting](https://mlsanity.com/paper/2102.07831/) (2021)
- [Mitigating Data Sparsity for Short Text Topic Modeling by Topic-Semantic Contrastive Learning](https://mlsanity.com/paper/2211.12878/) (2022)
- [Multimodal Categorization of Crisis Events in Social Media](https://mlsanity.com/paper/2004.04917/) (2020)
- [InfoCTM: A Mutual Information Maximization Perspective of Cross-Lingual Topic Modeling](https://mlsanity.com/paper/2304.03544/) (2023)
- [Improving Neural Cross-Lingual Summarization via Employing Optimal Transport Distance for Knowledge Distillation](https://mlsanity.com/paper/2112.03473/) (2021)
- [Enriching and Controlling Global Semantics for Text Summarization](https://mlsanity.com/paper/2109.10616/) (2021)
- [Adaptive Contrastive Learning on Multimodal Transformer for Review Helpfulness Predictions](https://mlsanity.com/paper/2211.03524/) (2022)
- [Decision trees as partitioning machines to characterize their generalization properties](https://mlsanity.com/paper/2010.07374/) (2020)
- [SANCL: Multimodal Review Helpfulness Prediction with Selective Attention and Natural Contrastive Learning](https://mlsanity.com/paper/2209.05040/) (2022)
- [Learning-to-Rank with Partitioned Preference: Fast Estimation for the Plackett-Luce Model](https://mlsanity.com/paper/2006.05067/) (2020)
- [Using Argument-based Features to Predict and Analyse Review Helpfulness](https://mlsanity.com/paper/1707.07279/) (2017)
- [Self-Attentive Document Interaction Networks for Permutation Equivariant Ranking](https://mlsanity.com/paper/1910.09676/) (2019)

## Built on by (most cited first, 7 of 7)

- [Modeling Dynamic Topics in Chain-Free Fashion by Evolution-Tracking Contrastive Learning and Unassociated Word Exclusion](https://mlsanity.com/paper/2405.17957/) (2024)
- [Improving Multimodal Sentiment Analysis: Supervised Angular Margin-based Contrastive Learning for Enhanced Fusion Representation](https://mlsanity.com/paper/2312.02227/) (2023)
- [DemaFormer: Damped Exponential Moving Average Transformer with Energy-Based Modeling for Temporal Language Grounding](https://mlsanity.com/paper/2312.02549/) (2023)
- [Encoding and Controlling Global Semantics for Long-form Video Question Answering](https://mlsanity.com/paper/2405.19723/) (2024)
- [Expand BERT Representation with Visual Information via Grounded Language Learning with Multimodal Partial Alignment](https://mlsanity.com/paper/2312.01592/) (2023)
- [Topic-aware Causal Intervention for Counterfactual Detection](https://mlsanity.com/paper/2409.16668/) (2024)
- [PREMISE: Matching-based Prediction for Accurate Review Recommendation](https://mlsanity.com/paper/2505.01255/) (2025)

## Abstract (arXiv)

Multimodal Review Helpfulness Prediction (MRHP) aims to rank product reviews based on predicted helpfulness scores and has been widely applied in e-commerce via presenting customers with useful reviews. Previous studies commonly employ fully-connected neural networks (FCNNs) as the final score predictor and pairwise loss as the training objective. However, FCNNs have been shown to perform inefficient splitting for review features, making the model difficult to clearly differentiate helpful from unhelpful reviews. Furthermore, pairwise objective, which works on review pairs, may not completely capture the MRHP goal to produce the ranking for the entire review list, and possibly induces low generalization during testing. To address these issues, we propose a listwise attention network that clearly captures the MRHP ranking context and a listwise optimization objective that enhances model generalization. We further propose gradient-boosted decision tree as the score predictor to efficaciously partition product reviews' representations. Extensive experiments demonstrate that our method achieves state-of-the-art results and polished generalization performance on two large-scale MRHP benchmark datasets.