检索结果-内蒙古大学图书馆

Using Large Language Models to Detect Depression From User-Generated Diary text data as a Novel Approach in Digital Mental Health Screening: Instrument Validation Study

引用

JOURNAL OF MEDICAL INTERNET RESEARCH 2024年 26卷 e54617页

作者： Shin, Daun Kim, Hyoseung Lee, Seunghwan Cho, Younhee Jung, Whanbo Korea Univ Anam Hosp Dept Psychiat 73 Goryeodae Ro Seoul 02841 South Korea Doctorpresso Seoul South Korea VOLTWIN Seoul South Korea Seoul Natl Univ Dept Design Seoul South Korea

Background: Depressive disorders have substantial global implications, leading to various social consequences, including decreased occupational productivity and a high disability burden. Early detection and intervention for clinically significant depression have gained attention;however, the existing depression screening tools, such as the Center for Epidemiologic Studies Depression Scale, have limitations in objectivity and accuracy. Therefore, researchers are identifying objective indicators of depression, including image analysis, blood biomarkers, and ecological momentary assessments (EMAs). Among EMAs, user-generated text data, particularly from diary writing, have emerged as a clinically significant and analyzable source for detecting or diagnosing depression, leveraging advancements in large language models such as ChatGPT. Objective: We aimed to detect depression based on user-generated diary text through an emotional diary writing app using a large language model (LLM). We aimed to validate the value of the semistructured diary text data as an EMA data source. Methods: Participants were assessed for depression using the Patient Health Questionnaire and suicide risk was evaluated using the Beck Scale for Suicide Ideation before starting and after completing the 2-week diary writing period. The text data from thedaily diaries were also used in the analysis. The performance of leading LLMs, such as ChatGPT with GPT-3.5 and GPT-4, was assessed with and without GPT-3.5 fine-tuning on the training data set. The model performance comparison involved the use of chain-of-thought and zero-shot prompting to analyze the text structure and content. Results: We used 428 diaries from 91 participants;GPT-3.5 fine-tuning demonstrated superior performance in depression detection, achieving an accuracy of 0.902 and a specificity of 0.955. However, the balanced accuracy was the highest (0.844) forGPT-3.5 without fine-tuning and prompt techniques;it displayed a recall of 0.929.

关键词： depression screening artificial intelligence digital health technology text data

来源：评论

学校读者我要写书评

暂无评论

Propaganda Detection in text data Based on NLP and Machine Learning 2

Propaganda Detection in Text Data Based on NLP and Machine L...

引用

2nd International Workshop on Modern Machine Learning Technologies and data Science (MoMLeT+DS)

作者： Oliinyk, Vitaliia-Anna Vysotska, Victoria Burov, Yevhen Mykich, Khrystyna Basto-Fernandes, Vitor Lviv Polytech Natl Univ Lvov Ukraine Univ Inst Lisbon Lisbon Portugal

The goal of this research is to build a machine-learning model, as well as preliminary data process and feature extraction algorithms that would allow to successfully identify signs of propaganda in text data and to solve a binary classification task. The task is presented in two forms: article level propaganda detection and sentence level propaganda detection. The propaganda detection dataset for this level of task consists of 35 993 articles (including headlines) written in English. Each article is marked as either "propaganda" or "non-propaganda". The dataset also contains unique identifier for each article.

关键词： Content text data Propaganda Detection data Classification Machine Learning

来源：评论

学校读者我要写书评

暂无评论

Graph Community Detection: Normalized Compression Distance Based Implementation for text data 3rd

Graph Community Detection: Normalized Compression Distance B...

引用

3rd International Afro-European Conference for Industrial Advancement (AECIA)

作者： Sanwaliya, Abhishek Chinnamgari, Sunil K. Desai, Abhishek Saha, Arijit Fidel Investments Data Scientist Business Analyt & Res Bangalore Karnataka India

ISBN: (纸本)9783319608341;9783319608334

Community detection algorithms are widely used to study the structural properties of real-world networks. In this paper, we experimentally evaluate the qualitative performance of several community detection algorithms based on normalized compression distance (NCD) using diversified datasets like documents, feeds, articles and blogs. We compare the quality of the algorithms based on F-score measure. text data when given as input to NCD performs better when compare to conventional feed like document term matrix as input. Finally, we reveal that label propagation community detection algorithm is more suitable for clustering text data as compare to other community detection algorithms and it creates more distinct communities on diversified data.

关键词： Graph community detection Normalized compression distance NLP Machine learning text data

来源：评论

学校读者我要写书评

暂无评论

Evaluate H2Hadoop and Amazon EMR performances by processing MR jobs in text data Sets

Evaluate H2Hadoop and Amazon EMR performances by processing ...

引用

IEEE Long Island Systems, Applications and Technology Conference (LISAT)

作者： Alshammari, Hamoud Lee, Jeongkyu Bajwa, Hassan Univ Bridgeport Dept Comp Sci 221 Univ Ave Bridgeport CT 06604 USA Univ Bridgeport Dept Elect Engn 221 Univ Ave Bridgeport CT USA

ISBN: (纸本)9781467384902

text data is defined as sequences of characters that may become big data that has no specific format and only can be processed using the original Hadoop. Amazon Web Services AWS provides virtual Cloud Computing services such as storing data using S3 service and processing big data using EMR service. Amazon Elastic MapReduce EMR uses the original Hadoop as a processing environment to its Cloud Computing services. Also, H2Hadoop is a developed version of Hadoop that provides big data processing service that uses the metadata of related jobs to improve Hadoop performance. In this paper, we process a find sequence job in text data using Amazon EMR and H2Hadoop, and we came up with a comparison between them that shows H2Hadoop performance is more efficient than Amazon EMR in some cases under different considerations.

关键词： Bigdata Cloud Computing Hadoop H2Hadoop Amazon EMR text data

来源：评论

学校读者我要写书评

暂无评论

Hiding text data in Image through Image Watermarking using DCT & DWT: A Research Paper

Hiding Text Data in Image through Image Watermarking using D...

引用

IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (IEEE ICPCSI)

作者： Gupta, Garima Khunteta, Ajay Poornima Coll Engn Dept Comp Sci & Engn Jaipur Rajasthan India

ISBN: (纸本)9781538608142

image watermarking is an important and a complex task if done with the high security parameters, in this paper the main focus is over the raising the complexity level of the hiding algorithm, hence there have been as many as three proper major equations which are used to hide the secrete text data inside an image. along with three major and minor equations there have been few more complex steps like dwt which have been used to keep the watermarked image quality high on different parameters. image watermarking is a significant and compound feature of information security. digital watermarking is the procedure of embedding information into a digital signal in a manner that is not easy to remove. watermarking is an hidden text embedded within an image to explain authenticity or verification of holder ship. a digital watermark is a blueprint of bits embed into a digital image, audio or video file. in this paper the center of attention is on the text data watermarking to achieve the preferred outcome there are several techniques which are going to be discussed in this paper. the techniques which are going to be discuss.

关键词： Frequency domain Spatial domain text data watermarking

来源：评论

学校读者我要写书评

暂无评论

Torpedo: Topic Periodicity Discovery from text data 3

Torpedo: Topic Periodicity Discovery from Text Data

引用

Conference on Next-Generation Analyst III

作者： Wang, Jingjing Deng, Hongbo Han, Jiawei Univ Illinois Urbana IL 61801 USA Yahoo Labs Sunnyvale CA USA

ISBN: (纸本)9781628416152

Although history may not repeat itself, many human activities are inherently periodic, recurring daily, weekly, monthly, yearly or following some other periods. Such recurring activities may not repeat the same set of keywords, but they do share similar topics. Thus it is interesting to mine topic periodicity from text data instead of just looking at the temporal behavior of a single keyword/phrase. Some previous preliminary studies in this direction prespecify a periodic temporal template for each topic. In this paper, we remove this restriction and propose a simple yet effective framework Torpedo to mine periodic/recurrent patterns from text, such as news articles, search query logs, research papers, and web blogs. We first transform text data into topic-specific time series by a time dependent topic modeling module, where each of the time series characterizes the temporal behavior of a topic. Then we use time series techniques to detect periodicity. Hence we both obtain a clear view of how topics distribute over time and enable the automatic discovery of periods that are inherent in each topic. Theoretical and experimental analyses demonstrate the advantage of Torpedo over existing work.

关键词： Topic periodicity text data time dependent topic modeling

来源：评论

学校读者我要写书评

暂无评论

FASTINJECT: INJECTING UNPAIRED text data INTO CTC-BASED ASR TRAINING 49

FASTINJECT: INJECTING UNPAIRED TEXT DATA INTO CTC-BASED ASR ...

引用

49th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Deng, Keqi Woodland, Philip C. Univ Cambridge Dept Engn Trumpington St Cambridge England

ISBN: (纸本)9798350344868;9798350344851

Recently, connectionist temporal classification (CTC)-based end-to-end (E2E) automatic speech recognition (ASR) models have achieved impressive results, especially with the development of self-supervised learning. However, E2E ASR models trained on paired speech-text data often suffer from domain shifts from training to testing. To alleviate this issue, this paper proposes a flat-start joint training method, named FastInject, which efficiently injects multi-domain unpaired text data into CTC-based ASR training. To maintain training efficiency, text units are pre-upsampled, and their representations are fed into the CTC model along with speech features. To bridge the modality gap between speech and text, an attention-based modality matching mechanism (AM3) is proposed, which retains the E2E flat-start training. Experiments show that the proposed FastInject gave a 22% relative WER reduction (WERR) for intra-domain Librispeech-100h data and 20% relative WERR on out-of-domain test sets.

关键词： ASR CTC text data domain shifts

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study on Feature Selection Techniques for Multi-cluster text data 4th

引用

4th International Conference on Harmony Search, Soft Computing and Applications (ICHSA)

作者： Gupta, Ananya Begum, Shahin Ara Assam Univ Dept Comp Sci Silchar 788011 India

ISBN: (纸本)9789811307614;9789811307607

text clustering involves data that are of very high dimension. Feature selection techniques find subsets of relevant features from the original feature space that help in efficient and effective clustering. Selection of relevant features merely on ranking scores without considering correlation interferes with the clustering performance. An efficient feature selection technique should be capable of preserving the multi-cluster structure of the data. The purpose of the present work is to demonstrate that feature selection techniques which take into consideration the correlation among features in multi-cluster scenario show better clustering results than those techniques that simply rank features independent of each other. This paper compares two feature selection techniques in this regard viz. the traditional Tf-Idf and the Multi-Cluster Feature Selection (MCFS) technique. The experimental results over the TDT2 and Reuters-21,578 datasets show the superior clustering results of MCFS over traditional Tf-Idf.

关键词： Feature selection Multi-Cluster feature selection Tf-Idf Clustering text data

来源：评论

学校读者我要写书评

暂无评论

WordGraph: A Python Package for Reconstructing Interactive Causal Graphical Models from text data 24

WordGraph: A Python Package for Reconstructing Interactive C...

引用

17th ACM International Conference on Web Search and data Mining (WSDM)

作者： Ferdjaoui, Amine Affeldt, Severine Nadif, Mohamed Univ Paris Cite SogetiLabs Paris France Univ Paris Cite Ctr Borelli Paris France Univ Paris Cite Ctr Borelli UMR 9010 Paris France

ISBN: (纸本)9798400703713

We present WordGraph, a Python package for exploring the topics of documents corpora. WordGraph provides causal graphical models from text data vocabulary and proposes interactive visualizations of terms networks. Our ease-to-use package is provided with a prebuilt pipeline to access the main modules through jupyter widgets. It results in the encapsulation of a whole vocabulary exploration process within a single jupyter notebook cell, with straightforward parameters settings and interactive plots. WordGraph pipeline is fully customizable by adding/removing widgets or changing default parameters. To assist users with no background in Python nor jupyter notebook, but willing to explore large corpora topics, we also propose an automatic dashboard generation from the customizable jupyter notebook pipeline in a web application style. WordGraph is available through a GitHub repository.

关键词： co-clustering causal network reconstruction text data

来源：评论

学校读者我要写书评

暂无评论

Selectivity Estimation for Extraction Operators over text data

Selectivity Estimation for Extraction Operators over Text Da...

引用

IEEE 27th International Conference on data Engineering (ICDE 2011)

作者： Wang, Daisy Zhe Wei, Long Li, Yunyao Reiss, Frederick Vaithyanathan, Shivakumar Univ Calif Berkeley Berkeley CA 94720 USA IBM Corp Almaden Res Ctr San Jose CA 95120 USA

ISBN: (纸本)9781424489589

Recently, there has been increasing interest in extending relational query processing to efficiently support extraction operators, such as dictionaries and regular expressions, over text data. Many text processing queries are sophisticated in that they involve multiple extraction and join operators, resulting in many possible query plans. However, there has been little research on building the selectivity or cost estimation for these extraction operators, which is crucial for an optimizer to pick a good query plan. In this paper, we define the problem of selectivity estimation for dictionaries and regular expressions, and propose to develop document synopses over a text corpus, from which the selectivity can be estimated. We first adapt the language models in the Natural Language Processing literature to form the top-k n-gram synopsis as the baseline document synopsis. Then we develop two classes of novel document synopses: stratified bloom filter synopsis and roll-up synopsis. We also develop techniques to decompose a complicated regular expression into subparts to achieve more effective and accurate estimation. We conduct experiments over the Enron email corpus using both real-world and synthetic workloads to compare the accuracy of the selectivity estimation over different classes and variations of synopses. The results show that, the top-k stratified bloom filter synopsis and the roll-up synopsis is the most accurate in dictionary and regular expression selectivity estimation respectively.

关键词： Accuracy Adaptation model Arrays Blogs data mining Dictionaries Enron email corpus Estimation data structures database management dictionaries dictionaries document synopses extraction operators join operators natural language processing natural language processing query processing regular expressions relational query processing roll-up synopsis selectivity estimation text analysis text data text processing queries top-k stratified bloom filter synopsis

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：