In the marketing field, understanding consumer heterogeneity, which is the
internal or psychological difference among consumers that cannot be captured by
behavioral logs, has long been a critical challenge. However, a number of
consumers today usually post their evaluation on the specific product on the
online platform, which can be the valuable source of such unobservable
differences among consumers. Several previous studies have shown the validity
of the analysis on text modality, but on the other hand, such analyses may not
necessarily demonstrate sufficient predictive accuracy for text alone, as they
may not include information readily available from cross-sectional data, such
as consumer profile data. In addition, recent advances in machine learning
techniques, such as large-scale language models (LLMs) and multimodal learning
have made it possible to deal with the various kind of dataset simultaneously,
including textual data and the traditional cross-sectional data, and the joint
representations can be effectively obtained from multiple modalities.
Therefore, this study constructs a product evaluation model that takes into
account consumer heterogeneity by multimodal learning of online product reviews
and consumer profile information. We also compare multiple models using
different modalities or hyper-parameters to demonstrate the robustness of
multimodal learning in marketing analysis.

本研究构建了一个产品评价模型，通过多模态学习在线产品评价和消费者个人信息，考虑了消费者异质性，同时比较了不同模态或超参数的多个模型，以展示多模态学习在营销分析中的稳健性。

利用口碑文本和人口统计学的多模态深度学习预测客户评分：在市场营销中处理消费者异质性

Multimodal Deep Learning of Word-of-Mouth Text and Demographics to  Predict Customer Rating: Handling Consumer Heterogeneity in Marketing

Online reviews enable consumers to engage with companies and provide
important feedback. Due to the complexity of the high-dimensional text, these
reviews are often simplified as a single numerical score, e.g., ratings or
sentiment scores. This work empirically examines the causal effects of
user-generated online reviews on a granular level: we consider multiple
aspects, e.g., the Food and Service of a restaurant. Understanding consumers'
opinions toward different aspects can help evaluate business performance in
detail and strategize business operations effectively. Specifically, we aim to
answer interventional questions such as What will the restaurant popularity be
if the quality w.r.t. its aspect Service is increased by 10%? The defining
challenge of causal inference with observational data is the presence of
"confounder", which might not be observed or measured, e.g., consumers'
preference to food type, rendering the estimated effects biased and
high-variance. To address this challenge, we have recourse to the multi-modal
proxies such as the consumer profile information and interactions between
consumers and businesses. We show how to effectively leverage the rich
information to identify and estimate causal effects of multiple aspects
embedded in online reviews. Empirical evaluations on synthetic and real-world
data corroborate the efficacy and shed light on the actionable insight of the
proposed approach.

本研究通过分析多个方面的包括食品和服务等的用户生成的在线评论，使用观察数据识别并估计各方面的因果效应，并提出了一种利用多模态变量的方法，如消费者个人信息和消费者与企业之间的互动，以克服隐变量存在的挑战。实证评估表明该方法的有效性并为用户提供了可行的深层次的洞见。