Effects of Multi-Aspect Online Reviews with Unobserved Confounders: Estimation and Implication

• URL: http://arxiv.org/abs/2110.01746v1
• Date: Mon, 4 Oct 2021 23:38:21 GMT
• Title: Effects of Multi-Aspect Online Reviews with Unobserved Confounders: Estimation and Implication
• Authors: Lu Cheng, Ruocheng Guo, Kasim Selcuk Candan, Huan Liu
• Abstract summary: We study the effects of online reviews on business revenue and direct effects with the numerical cause -- ratings -- being the mediator. We draw on recent advances in machine learning and causal inference to together estimate the hidden confounders and causal effects. We present empirical evaluations using real-world examples to discuss the importance and implications of differentiating the multi-aspect effects in strategizing business operations.
• Score: 19.74820808192969
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Online review systems are the primary means through which many businesses seek to build the brand and spread their messages. Prior research studying the effects of online reviews has been mainly focused on a single numerical cause, e.g., ratings or sentiment scores. We argue that such notions of causes entail three key limitations: they solely consider the effects of single numerical causes and ignore different effects of multiple aspects -- e.g., Food, Service -- embedded in the textual reviews; they assume the absence of hidden confounders in observational studies, e.g., consumers' personal preferences; and they overlook the indirect effects of numerical causes that can potentially cancel out the effect of textual reviews on business revenue. We thereby propose an alternative perspective to this single-cause-based effect estimation of online reviews: in the presence of hidden confounders, we consider multi-aspect textual reviews, particularly, their total effects on business revenue and direct effects with the numerical cause -- ratings -- being the mediator. We draw on recent advances in machine learning and causal inference to together estimate the hidden confounders and causal effects. We present empirical evaluations using real-world examples to discuss the importance and implications of differentiating the multi-aspect effects in strategizing business operations.

Related papers

• Impact of Tone-Aware Explanations in Recommender Systems [11.774563966512709]
  In recommender systems, the presentation of explanations plays a crucial role in supporting users' decision-making processes. This study investigates the effect of explanation tones through an online user study from three aspects: perceived effects, domain differences, and user attributes.
  arXiv  Detail & Related papers  (2024-05-08T13:55:52Z)
• Decoding Susceptibility: Modeling Misbelief to Misinformation Through a Computational Approach [61.04606493712002]
  Susceptibility to misinformation describes the degree of belief in unverifiable claims that is not observable. Existing susceptibility studies heavily rely on self-reported beliefs. We propose a computational approach to model users' latent susceptibility levels.
  arXiv  Detail & Related papers  (2023-11-16T07:22:56Z)
• A Taxonomy of Rater Disagreements: Surveying Challenges & Opportunities from the Perspective of Annotating Online Toxicity [15.23055494327071]
  Toxicity is an increasingly common and severe issue in online spaces. A rich line of machine learning research has focused on computationally detecting and mitigating online toxicity. Recent research has pointed out the importance of accounting for the subjective nature of this task.
  arXiv  Detail & Related papers  (2023-11-07T21:00:51Z)
• Decoding the Silent Majority: Inducing Belief Augmented Social Graph with Large Language Model for Response Forecasting [74.68371461260946]
  SocialSense is a framework that induces a belief-centered graph on top of an existent social network, along with graph-based propagation to capture social dynamics. Our method surpasses existing state-of-the-art in experimental evaluations for both zero-shot and supervised settings.
  arXiv  Detail & Related papers  (2023-10-20T06:17:02Z)
• DOMINO: Visual Causal Reasoning with Time-Dependent Phenomena [59.291745595756346]
  We propose a set of visual analytics methods that allow humans to participate in the discovery of causal relations associated with windows of time delay. Specifically, we leverage a well-established method, logic-based causality, to enable analysts to test the significance of potential causes. Since an effect can be a cause of other effects, we allow users to aggregate different temporal cause-effect relations found with our method into a visual flow diagram.
  arXiv  Detail & Related papers  (2023-03-12T03:40:21Z)
• Fair Effect Attribution in Parallel Online Experiments [57.13281584606437]
  A/B tests serve the purpose of reliably identifying the effect of changes introduced in online services. It is common for online platforms to run a large number of simultaneous experiments by splitting incoming user traffic randomly. Despite a perfect randomization between different groups, simultaneous experiments can interact with each other and create a negative impact on average population outcomes.
  arXiv  Detail & Related papers  (2022-10-15T17:15:51Z)
• The Invariant Ground Truth of Affect [2.570570340104555]
  Ground truth of affect is attributed to the affect labels which inadvertently include biases inherent to the subjective nature of emotion and its labeling. This paper reframes the ways one may obtain a reliable ground truth of affect by transferring aspects of causation theory to affective computing. We employ causation inspired methods for detecting outliers in affective corpora and building affect models that are robust across participants and tasks.
  arXiv  Detail & Related papers  (2022-10-14T08:26:01Z)
• Counterfactual Reasoning for Out-of-distribution Multimodal Sentiment Analysis [56.84237932819403]
  This paper aims to estimate and mitigate the bad effect of textual modality for strong OOD generalization. Inspired by this, we devise a model-agnostic counterfactual framework for multimodal sentiment analysis.
  arXiv  Detail & Related papers  (2022-07-24T03:57:40Z)
• Estimating Causal Effects of Multi-Aspect Online Reviews with Multi-Modal Proxies [24.246450472404614]
  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.
  arXiv  Detail & Related papers  (2021-12-19T22:29:02Z)
• Towards Unbiased Visual Emotion Recognition via Causal Intervention [63.74095927462]
  We propose a novel Emotion Recognition Network (IERN) to alleviate the negative effects brought by the dataset bias. A series of designed tests validate the effectiveness of IERN, and experiments on three emotion benchmarks demonstrate that IERN outperforms other state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-07-26T10:40:59Z)
• Text and Causal Inference: A Review of Using Text to Remove Confounding from Causal Estimates [15.69581581445705]
  An individual's entire history of social media posts or the content of a news article could provide a rich measurement of confounders. Despite increased attention on adjusting for confounding using text, there are still many open problems.
  arXiv  Detail & Related papers  (2020-05-01T23:20:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.