检索结果-内蒙古大学图书馆

text regression Analysis for Predictive Intervals Using Gradient Boosting 1

8th Future of Information and Communication Conference (FICC)

作者： Iliev, Alexander I. Raksha, Ankitha SRH Berlin Univ Berlin Germany Bulgarian Acad Sci Inst Math & Informat Sofia Bulgaria

ISBN: (数字)9783031280733

ISBN: (纸本)9783031280726;9783031280733

In this paper, we aim to explore text data analysis with the help of different methods to vectorize the data and carry out regression methods. At present, we have a lot of text categorization techniques, but very few algorithms are dedicated to text regression. But many regression models predict only a single estimated value. However, it's more efficient to predict a numerical range than a single estimate, since we can be more sure that the true value will be within the range rather than considering the estimated value as the true value. We aim to combine both these techniques in this paper. The goal of this paper is to collect text data, clean the data, and create a text regression model to find the best-suited algorithm that could be used in any situation, through the use of quantile regression.

关键词： text analysis tf-.idf word2vec GloVe text regression Word vectorization Quantile Gradient boosting Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Additive Feature Attribution Explainable Methods to Craft Adversarial Attacks for text Classification and text regression

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2023年第12期35卷 12400-12414页

作者： Chai, Yidong Liang, Ruicheng Samtani, Sagar Zhu, Hongyi Wang, Meng Liu, Yezheng Jiang, Yuanchun Hefei Univ Technol Sch Management Key Lab Philosophy & Social Sci Cyberspace Behav & Hefei 230009 Anhui Peoples R China Key Lab Proc Optimizat & Intelligent Decis Making Hefei 230009 Anhui Peoples R China Indiana Univ Kelley Sch Business Bloomington IN 47405 USA Univ Texas San Antonio Carlos Alvarez Coll Business San Antonio TX 78249 USA Hefei Univ Technol Sch Comp Sci & Informat Engn Hefei 230002 Anhui Peoples R China

Deep learning (DL) models have significantly improved the performance of text classification and text regression tasks. However, DL models are often strikingly vulnerable to adversarial attacks. Many researchers have aimed to develop adversarial attacks against DL models in realistic black-box settings (i.e., assuming no model knowledge is accessible to attackers). These attacks typically operate with a two-phase framework: (1) sensitivity estimation through gradient-based or deletion-based methods to evaluate the sensitivity of each token to the prediction of the target model, and (2) perturbation execution to craft adversarial examples based on the estimated token sensitivity. However, gradient-based and deletion-based methods used to estimate sensitivity often face issues of capturing token directionality and overlapping token sensitivities, respectively. In this study, we propose a novel eXplanation-based method for Adversarial text Attacks (XATA) that leverages additive feature attribution explainable methods, namely LIME or SHAP, to measure the sensitivity of input tokens when crafting black-box adversarial attacks on DL models performing text classification or text regression. We evaluated XATA's attack performance on DL models executing text classification on the IMDB Movie Review, Yelp Reviews-Polarity, and Amazon Reviews-Polarity datasets and DL models conducting text regression on the My Personality, Drug Review, and CommonLit Readability datasets. The proposed XATA outperformed the existing gradient-based and deletion-based adversarial attack baselines in both tasks. These findings indicate that the ever-growing research focused on improving the explainability of DL models with additive feature attribution explainable methods can provide attackers with weapons to launch targeted adversarial attacks.

关键词： Sensitivity text categorization Task analysis Mathematical models Closed box Additives Perturbation methods Adversarial attack additive feature attribution explainable methods text classification text regression

来源：评论

学校读者我要写书评

暂无评论

Interpretable deep learning based text regression for financial prediction

引用

EXPERT SYSTEMS 2023年第9期40卷 e13368-e13368页

作者： Liang, Rufeng Zhang, Weiwen Ye, Haiming Guangdong Univ Technol Sch Comp Sci & Technol Guangzhou Peoples R China

text regression is an important task in natural language processing (NLP), which aims to predict continuous numerical values associated with text. Previous work focused on linear text regression requiring manual feature selection for financial prediction. Recently, non-linear text regression through neural network models has become a trend. However, most models rely only on convolutional neural networks (CNN) and suffer from insufficient interpretability. In this paper, we propose a deep neural network model named EM-CBA for text regression and further interpret the model. The proposed model is powered by word EMbedding, CNN, Bidirectional long short-term memory (Bi-LSTM) and Attention mechanism. The proposed EM-CBA takes financial report texts as input and predicts a financial metric named return on assets (ROA). We conduct comprehensive experiments on a dataset about the reports of enterprises. Experimental results show that the proposed model provides more accurate predictions of enterprises' metrics than previous convolutional neural network models and other classical models. The validity of each module of the model is also verified. Finally, we demonstrate a way of performing analysis in words change and results errors to intuitively interpret the effect of different text inputs on the model. The analysis demonstrates that the model is able to use information about sentiment words to analyse their associated contexts to revise the predictions.

关键词： deep learning financial prediction natural language processing text regression

来源：评论

学校读者我要写书评

暂无评论

Predicting the helpfulness of online reviews using a scripts-enriched text regression model

引用

EXPERT SYSTEMS WITH APPLICATIONS 2017年 71卷 98-110页

作者： Ngo-Ye, Thomas L. Sinha, Atish P. Sen, Arun Alabama State Univ Dept Comp Informat Syst Coll Business Adm Montgomery AL 36101 USA Univ Wisconsin Lubar Sch Business Milwaukee WI 53201 USA Texas A&M Univ Mays Business Sch College Stn TX 77843 USA

In this paper, we examine the utility of script analysis for predicting the helpfulness of online customer reviews. We employ the lens of cognitive scripts and posit that people share a cognitive script for what constitutes a helpful review in a given domain. Conceptually, a script includes the salient elements that readers look for before determining whether a review is helpful. To operationalize the construct of cognitive script, we seek the help of human annotators and ask them to highlight phrases that they believe are important for determining review helpfulness. The words in the annotated phrases are collected and become part of the script lexicon for a given domain. The lexicon entries represent the shared conception of essential elements, which are key to the evaluation of review helpfulness. We employ the words in the script lexicon as features in a text regression model to predict review helpfulness. Furthermore, we develop and empirically validate a new approach for combining script analysis and dimension reduction. The purpose of the study is to propose a new method to predict review helpfulness and to evaluate the effectiveness and efficiency of the scripts-enriched model. To demonstrate the efficacy of the scripts enriched model, we compare it with benchmark models - a Baseline model and a bag-of-words (BOW) model. The results show that the scripts-enriched text regression model not only produces the highest accuracy, but also the lowest training, testing, and feature selection times. (C) 2016 Elsevier Ltd. All rights reserved.

关键词： Business intelligence Online customer reviews Review helpfulness Script theory Human annotation text regression

来源：评论

学校读者我要写书评

暂无评论

textRegress: A Python package for advanced regression analysis on long-form text data

SOFTWARE IMPACTS

引用

SOFTWARE IMPACTS 2025年 24卷

作者： Jiang, Jinhang Liu, Ben Peng, Weiyao Srinivasan, Karthik McKesson Corp 6555 State Hwy 161 Irving TX 75039 USA Walmart Inc 702 SW 8th St Bentonville AR 72716 USA Univ Kansas 1654 Naismith Dr Lawrence KS 66045 USA

textRegress is an open-source Python package that leverages state-of-the-art deep learning techniques to perform regression analysis on long-form text data. Departing from conventional text mining tools that are confined to classification, sentiment, or readability metrics, textRegress provides a unified framework for conducting predictive modeling of continuous outcomes. By integrating advanced encoding methods - including transformer-based embeddings, TF-IDF, and pre-trained Hugging Face models - with a robust PyTorch Lightning backend, textRegress efficiently processes long texts through automatic chunking and dynamic feature integration. Its flexible architecture and customizable training paradigms empower researchers and practitioners across diverse domains to deploy sophisticated regression models, fostering reproducibility and accelerating innovation in text analytics.

关键词： text regression Natural language processing Deep learning Information extraction Advanced text encoding Predictive modeling

来源：评论

学校读者我要写书评

暂无评论

The influence of reviewer engagement characteristics on online review helpfulness: A text regression model

引用

DECISION SUPPORT SYSTEMS 2014年第1期61卷 47-58页

作者： Ngo-Ye, Thomas L. Sinha, Atish P. Dalton State Coll Sch Business Dalton GA 30720 USA Univ Wisconsin Sheldon B Labor Sch Business Milwaukee WI 53201 USA

The era of Web 2.0 is witnessing the proliferation of online social media platforms, which develop new business models by leveraging user-generated content. One rapidly growing source of user-generated data is online reviews, which play a very important role in disseminating information, facilitating trust, and promoting commerce in the e-marketplace. In this paper, we develop and compare several text regression models for predicting the helpfulness of online reviews. In addition to using review words as predictors, we examine the influence of reviewer engagement characteristics such as reputation, commitment, and current activity. We employ a reviewer's RPM (Recency, Frequency, Monetary Value) dimensions to characterize his/her overall engagement and investigate if the inclusion of those dimensions helps improve the prediction of online review helpfulness. Empirical findings from text mining experiments conducted using reviews from Yelp and Amazon offer strong support to our thesis. We find that both review text and reviewer engagement characteristics help predict review helpfulness. The hybrid approach of combining the textual features of bag-of-words model and RPM dimensions produces the best prediction results. Furthermore, our approach facilitates the estimation of the helpfulness of new reviews instantly, making it possible for social media platforms to dynamically adjust the presentation of those reviews on their websites. (C) 2014 Elsevier B.V. All rights reserved.

关键词： Online review text regression Vector space model Reviewer engagement characteristics RFM analysis

来源：评论

学校读者我要写书评

暂无评论

FETILDA: Evaluation Framework for Effective Representations of Long Financial Documents

引用

ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA 2024年第7期18卷 1-27页

作者： Xia, Bolun (Namir) Rawte, Vipula Gupta, Aparna Zaki, Mohammed J. Rensselaer Polytech Inst Sch Sci Troy NY 12181 USA Rensselaer Polytech Inst Sch Sci Comp Sci Troy NY 12181 USA Rensselaer Polytech Inst Lally Sch Management Troy NY 12181 USA Rensselaer Polytech Inst Dept Comp Sci Troy NY 12181 USA

In the financial sphere, there is a wealth of accumulated unstructured financial data, such as the textual disclosure documents that companies submit on a regular basis to regulatory agencies, such as the Securities and Exchange Commission. These documents are typically very long and tend to contain valuable soft information about a company's performance that is not present in quantitative predictors. It is therefore of great interest to learn predictive models from these long textual documents, especially for forecasting numerical key performance indicators. In recent years, there has been great progress in natural language processing via pre-trained language models (LMs) learned from large corpora of textual data. This prompts the important question of whether they can be used effectively to produce representations for long documents, as well as how we can evaluate the effectiveness of representations produced by various LMs. Our work focuses on answering this critical question, namely, the evaluation of the efficacy of various LMs in extracting useful soft information from long textual documents for prediction tasks. In this article, we propose and implement a deep learning evaluation framework that utilizes a sequential chunking approach combined with an attention mechanism. We perform an extensive set of experiments on a collection of 10-K reports submitted annually by U.S. banks, and another dataset of reports submitted by U.S. companies, to investigate thoroughly the performance of different types of language models. Overall, our framework using LMs outperforms strong baseline methods for textual modeling as well as for numerical regression. Our work provides better insights into how utilizing pre-trained domain-specific and fine-tuned long-input LMs for representing long documents can improve the quality of representation of textual data and, therefore, help in improving predictive analyses.

关键词： text regression language models long text documents financial documents 10-K reports

来源：评论

学校读者我要写书评

暂无评论

An Automated Impasse Detection System Based on the Analysis of Self-Explanations in Mathematics 24

An Automated Impasse Detection System Based on the Analysis ...

引用

24th IEEE International Conference on Advanced Learning Technologies (ICALT)

作者： Nakamoto, Ryosuke Flanagan, Brendan Dai, Yiling Takami, Kyosuke Ogata, Hiroaki Kyoto Univ Grad Sch Informat Kyoto Japan Kyoto Univ Ctr Innovat Res & Educ Data Sci Kyoto Japan Kyoto Univ Acad Ctr Comp & Media Studies Kyoto Japan Natl Inst Educ Policy Res Tokyo Japan

ISBN: (纸本)9798350362060;9798350362053

In online mathematics education, self-explanation is increasingly recognized as a key tool for improving learning outcomes. Identifying learning impasses, which present significant educational challenges, is crucial. Typically, detecting these impasses demands considerable effort from educators to manually review and identify issues in students' mathematical *** paper introduces a fully automated impasse detection system designed for online math learning that leverages self-explanations. The system collects high-quality data from students working on the same quizzes, generates example answers, and uses these as benchmarks to identify where students are struggling. The system architecture is described in detail, focusing on the methods used to gather and validate high-quality self-explanation *** analysis using text regression models shows promising results: the models predict self-explanation scores with an error rate of 0.585 for validation data and 0.655 for evaluation data. While there are variations in scoring accuracy across different mathematical topics, the findings suggest that the system has the potential to significantly improve mathematics education by automating the detection of learning impasses.

关键词： Self-Explanation Auto Scoring text regression Online Mathematics Education

来源：评论

学校读者我要写书评

暂无评论

Using deep learning to analyse the times of the UN Security Council

引用

DIGITAL SCHOLARSHIP IN THE HUMANITIES 2024年第2期39卷 485-499页

作者： Blanke, Tobias Univ Amsterdam Inst Log Language & Computat Sci Pk 107 NL-1098 XG Amsterdam Netherlands

This article analyses how digital humanities scholarship can make use of recent advances in deep learning to analyse the temporal relations in an online textual archive. We use transfer learning as well as data augmentation techniques to investigate changes in United Nations Security Council resolutions. Instead of pre-defined periods, as it is common, we target the years directly. Such a text regression task is novel in the digital humanities as far as we can see and has the advantage of speaking directly to historical relations. We present not only very good experimental results but also demonstrate how such text regressions can be interpreted directly and with surrogate topic models.

关键词： Deep learning text regression transfer learning explainability United Nations Security Council

来源：评论

学校读者我要写书评

暂无评论

Automated post scoring: evaluating posts with topics and quoted posts in online forum

引用

WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS 2022年第3期25卷 1197-1221页

作者： Yang, Ruosong Cao, Jiannong Wen, Zhiyuan Shen, Jiaxing Hong Kong Polytech Univ Hung Hom Hong Kong Peoples R China

Online forumpost evaluationis an effective way for instructors to assess students' knowledge understanding and writing mechanics. Manually evaluating massive posts costs a lot of time. Automatically grading online posts could significantly alleviate instructors' burden. Similar text assessment tasks like Automated text Scoring evaluate the writing quality of independent texts or relevance between text and prompt. And Automatic Short Answer Grading measures the semantic matching of short answers according to given problems and correct answers. Different from existing tasks, we propose a novel task, Automated Post Scoring (APS), which grades all online discussion posts in each thread of each student with given topics and quoted posts. APS evaluates not only the writing quality of posts automatically but also the relevance to topics. To measure the relevance, we model the semantic consistency between posts and topics. Supporting arguments are also extracted from quoted posts to enhance posts evaluation. Specifically, we propose a mixture model including a hierarchical text model to measure the writing quality, a semantic matching model to model topic relevance, and a semantic representation model to integrate quoted posts. We also construct a new dataset called Online Discussion Dataset containing 2,542 online posts from 694 students of a social science course. The proposed models are evaluated on the dataset with correlation and residual based evaluation metrics. Compared with measuring posts alone, experimental results demonstrate that incorporating topics and quoted posts could improve the performance of APS by a large margin, more than 9 percent on QWK.

关键词： Automated post scoring text regression text mining Deep learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：