arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.20531cs.CV
收藏

一种轻量级的视觉-语言融合框架,用于从用户界面和元数据预测应用评分

A Lightweight Vision-Language Fusion Framework for Predicting App Ratings from User Interfaces and Metadata

Department of Computer Science, American International University–Bangladesh(计算机科学系,美国国际大学-孟加拉)

Azrin Sultana, Firoz Ahmed

AI总结:

本文提出了一种轻量级视觉-语言融合框架,通过结合UI和语义信息预测应用评分,实现了高精度的预测效果。

摘要:

应用评分是衡量移动应用质量、易用性和整体用户满意度的最重要指标之一。然而,现有的应用评分预测模型大多局限于文本数据或用户界面(UI)特征,忽视了联合利用UI和语义信息的重要性。为了解决这些限制,本研究提出了一种轻量级的视觉-语言框架,该框架整合了移动UI和语义信息以进行应用评分预测。该框架结合MobileNetV3提取UI布局的视觉特征,并结合DistilBERT提取文本特征。这些多模态特征通过带有Swish激活的门控融合模块进行融合,随后通过多层感知机(MLP)回归头进行处理。所提出的模型通过均方误差(MAE)、均方根误差(RMSE)、均方误差(MSE)、决定系数(R2)和皮尔逊相关系数进行评估。在训练20个周期后,模型实现了MAE为0.1060,RMSE为0.1433,MSE为0.0205,R2为0.8529,以及皮尔逊相关系数为0.9251。广泛的消融研究进一步证明了不同视觉和文本编码器组合的有效性。总体而言,所提出的轻量级框架为开发者和终端用户提供了有价值的见解,支持可持续的应用开发,并实现了在边缘设备上的高效部署。

英文摘要:

App ratings are among the most significant indicators of the quality, usability, and overall user satisfaction of mobile applications. However, existing app rating prediction models are largely limited to textual data or user interface (UI) features, overlooking the importance of jointly leveraging UI and semantic information. To address these limitations, this study proposes a lightweight vision--language framework that integrates both mobile UI and semantic information for app rating prediction. The framework combines MobileNetV3 to extract visual features from UI layouts and DistilBERT to extract textual features. These multimodal features are fused through a gated fusion module with Swish activations, followed by a multilayer perceptron (MLP) regression head. The proposed model is evaluated using mean absolute error (MAE), root mean square error (RMSE), mean squared error (MSE), coefficient of determination (R2), and Pearson correlation. After training for 20 epochs, the model achieves an MAE of 0.1060, an RMSE of 0.1433, an MSE of 0.0205, an R2 of 0.8529, and a Pearson correlation of 0.9251. Extensive ablation studies further demonstrate the effectiveness of different combinations of visual and textual encoders. Overall, the proposed lightweight framework provides valuable insights for developers and end users, supports sustainable app development, and enables efficient deployment on edge devices.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑