Leveraging Generative Intelligence in Digital Libraries : Towards Human-Machine Collaboration : 25th International Conference on Asia-Pacific Digital Libraries, ICADL 2023 Taipei, Taiwan, December 4-7, 2023 Proceedings, Part I / / Dion H. Goh, Shu-Jiun Chen, and Suppawong Tuarob, editors

• Pubblicazione: Singapore : , : Springer, , [2023]; ©2023
• Edizione: First edition.
• Descrizione fisica: 1 online resource (279 pages)
• Disciplina: 025.00285
• Soggetto topico: Digital libraries; Digital libraries - Asia; Digital libraries - Pacific Area
• Persona (resp. second.): GohDion H.; ChenShu-Jiun; TuarobSuppawong
• Nota di bibliografia: Includes bibliographical references and index.
• Nota di contenuto: Intro -- Preface -- Organization -- Contents - Part I -- Contents - Part II -- GAI and Digital Libraries -- Enhancing the Learning of Chinese Poem Creation Through an Auto-Generation and Evaluation System -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Automatic Generation System -- 3.2 Rule Judgment Subsystem -- 3.3 Scoring Subsystem -- 4 User Experiment -- 4.1 Experimental Design -- 4.2 Analysis Methods and Results -- 5 Discussion -- 6 Conclusions and Future Work -- References -- Evaluating the Use of Generative LLMs for Intralingual Diachronic Translation of Middle-Polish Texts into Contemporary Polish -- 1 Introduction -- 2 Related Work -- 3 Annotation with ChatGPT -- 4 Experiments -- 5 Evaluation -- 5.1 Automatic Evaluation -- 5.2 Human Evaluation -- 6 Conclusions -- References -- HistoChatbot: Educating History by Generating Quizzes in Social Network Services -- 1 Introduction -- 2 History-Related Data Collection -- 3 History-Focused Quiz Posting -- 4 Conclusions and Future Work -- References -- Investigation of ChatGPT Use in Research Data Retrieval -- 1 Introduction -- 2 Method -- 3 Results -- 4 Discussion -- 4.1 Comparison with Keyword Search -- 4.2 Characteristics of Research Data to Be Answered by ChatGPT -- 4.3 Devising Inputs to ChatGPT -- 4.4 About the Papers We Used -- 4.5 About the LLM Used -- 5 Conclusion -- References -- Aspect-Based Sentiment Analysis of Racial Issues in Singapore: Enhancing Model Performance Using ChatGPT -- 1 Introduction -- 2 Literature Review -- 2.1 Introduction to Aspect-Based Sentiment Analysis (ABSA) -- 2.2 Review of Race-Related Studies in Singapore -- 2.3 Existing Approaches to Address Data Imbalance -- 2.4 In-Context Learning -- 3 Methodology: ABSA for Social Media Analysis -- 3.1 Data Preparation -- 3.2 Method 1 - A Fine-Tuned ABSA Model. ; 3.3 Method 2 - Enhancing the Fine-Tuned ABSA Model Using ChatGPT: Addressing Data Imbalance -- 3.4 Method 3 - Improving the Fine-Tuned ABSA Model via In-context Learning -- 3.5 Performance Comparison -- 4 Analysis of Racial Issues in Singapore -- 5 Discussion -- 5.1 Limitations and Challenges -- 5.2 Implications for Future Research -- 6 Conclusion -- References -- Cultural Data Analysis -- Text Line Detection in Historical Index Tables: Evaluations on a New French PArish REcord Survey Dataset (PARES) -- 1 Introduction -- 2 Historical Index Table Dataset: PARES -- 2.1 PARES Dataset Description -- 2.2 Document Layout and Annotations -- 3 Document Image Analysis -- 4 Baselines for Text Line Extraction -- 4.1 Data Splits and Pre-processing -- 4.2 Implementations and Experiments -- 4.3 Results -- 5 Conclusion -- References -- Benchmarking NAS for Article Separation in Historical Newspapers -- 1 Introduction -- 2 The NAS Dataset -- 2.1 Annotation Guidelines -- 2.2 Statistics -- 3 Performance Evaluation Measures -- 3.1 Article Error Rate -- 3.2 Article Coverage Score -- 3.3 Proper Predicted Article -- 3.4 Segmentation -- 4 Experiments and Results -- 5 Conclusions -- References -- STRAS: A Semantic Textual-Cues Leveraged Rule-Based Approach for Article Separation in Historical Newspapers -- 1 Introduction -- 2 Preliminaries -- 2.1 Word Embedding Methods -- 2.2 Pre-trained Language Models -- 2.3 Newspaper Layout Analysis -- 3 Related Work -- 4 Proposed Methodology -- 4.1 Text-Region Embedding Generation -- 4.2 Text-Regions Similarity Computation and Categorization -- 4.3 Rule-Based Article Extraction -- 5 Datasets and Performance Evaluations Metrics -- 5.1 Data -- 5.2 Evaluation Metrics -- 6 Experiments and Results -- 6.1 Experimental Settings and Comparative Analysis -- 6.2 Results Discussion -- 7 Conclusions and Future Outlook -- References. ; Cultural Research Trends of Taiwan's Indigenous Peoples, 2000-2021 -- 1 Introduction -- 2 Literature Review -- 3 Research Methodology -- 4 Results of the Information Analysis -- 4.1 Distribution of Literature Publication Eras -- 4.2 Distribution of Research Methods -- 4.3 Distribution of Research Topics -- 5 Findings and Recommendations -- References -- Integration Between Humanities and Technology: Using Digital Humanities Technology to Read the Gospel of Matthew -- 1 Introduction -- 2 Using Digital Humanities to Interpret the Gospel of Matthew -- 3 Changes in Students' Understanding of Textual Analysis and Digital Humanities -- 3.1 Learning Outcomes -- 3.2 Interview Responses -- 4 Conclusion -- References -- Social Media Analytics -- Appraisal of Paradise: A Sentiment Analysis Dataset of French Tourists' Experiences in French Polynesia -- 1 Introduction -- 2 Context of the Dataset -- 3 Dataset Presentation -- 3.1 Triplets -- 3.2 Data Preprocessing -- 3.3 Data Annotation -- 3.4 Curation of the Data -- 4 Dataset Features -- 5 Created Datasets -- 6 Data Format -- 7 Future Work -- 8 Conclusion -- 9 Limitations -- References -- SLHCat: Mapping Wikipedia Categories and Lists to DBpedia by Leveraging Semantic, Lexical, and Hierarchical Features -- 1 Introduction -- 2 Related Work -- 2.1 Ontology Alignment -- 2.2 CaLiGraph and Cat2Ax -- 2.3 Distant Supervision -- 2.4 Prompt-Based Learning -- 3 Problem Definition and Overview -- 4 Methodology -- 4.1 Model Architecture -- 4.2 Root Phrase Extraction -- 4.3 Sentence Embedding for Matching by Semantic Similarities -- 4.4 Propagating Classes Through CaLiGraph Hierarchy -- 4.5 Named Entity Typing on Wikipedia Article Titles -- 4.6 Resolving Results Predicted by Multiple Methods -- 4.7 BERT Finetuning -- 5 Experiments -- 5.1 Benchmark Dataset Construction -- 5.2 Experimental Settings -- 5.3 Results and Discussions. ; 6 Conclusion and Future work -- References -- Quantitative Analysis of Scholarly References on YouTube *12pt -- 1 Introduction -- 2 Related Work -- 3 Materials and Methods -- 4 Results and Discussion -- 4.1 Temporal Changes in the Number of Scholarly References and the Videos and Channels Associated with Them -- 4.2 Trends in Research Fields of Scholarly References and Characteristics of the Most Common Channels for Uploading Videos Associated with These References -- 5 Conclusion -- References -- TweetVi: A Tweet Visualisation Dashboard for Automatic Topic Classification and Sentiment Analysis -- 1 Introduction -- 2 TweetVi Conceptualisation -- 2.1 Data Collection and Preprocessing -- 2.2 Filtering -- 2.3 Topic Modeling -- 3 TweetVi Demonstration -- References -- Health Information Encountering: Topic Modelling and Sentiment Analysis of Pre- and Current-COVID-19 Tweets -- 1 Introduction -- 2 Related Works -- 2.1 Eliciting Health-Related Information -- 2.2 Information Encountering -- 3 Methodology -- 3.1 Data Collection -- 3.2 Topic Modelling and Sentiment Analysis -- 4 Results -- 4.1 Topic Modelling Results -- 4.2 Sentiment Analysis Results -- 5 Discussion -- 6 Conclusion -- References -- Information Retrieval -- Analyzing Web Search Queries of Before and After Purchase on e-Commerce Site -- 1 Introduction -- 2 Data -- 3 Extraction of Characteristic Words Used During Pre- And Post-purchase Queries and Their Classification into Query Intents -- 4 Time Series Analysis of Queries Based on Query Intents -- 4.1 Occurrences of Query Intents per 24 h -- 4.2 Occurrence of Query Intents per Query -- 5 Conclusion -- References -- Web Page Evaluation and Opinion Formation on Controversial Search Topics -- 1 Introduction -- 2 Related Work -- 2.1 Controversial Topics -- 2.2 Search Behavior -- 2.3 Opinion Formation -- 3 Methods -- 3.1 Procedure -- 3.2 Topics. ; 3.3 Pretask Questionnaire -- 3.4 Search Task -- 3.5 Posttask Questionnaire -- 3.6 Interview -- 3.7 Participants -- 4 Results -- 4.1 Web Page Evaluations Analysis -- 4.2 Opinion Formation Analysis -- 5 Discussion -- 5.1 Implications -- 5.2 Limitations -- 6 Conclusion -- References -- Applying a Vector Search Method in Reference Service Question-Answer Retrieval Systems -- 1 Introduction -- 2 Data Collection -- 3 System Implementation -- 3.1 System Architecture -- 3.2 Sentence-BERT (SBERT) -- 3.3 ElasticSearch (ES) -- 4 Conclusion and Future Work -- References -- QRDP: A System that Facilitates the Selection of English Materials for Translator Education -- 1 Introduction -- 2 Background -- 2.1 Translation as a Documentational Process -- 2.2 Selecting Materials for Translation Practice -- 3 Facilitating the Selection of Translation Materials -- 3.1 Requirements for the System -- 3.2 QRDP: The System Prototype -- 4 Conclusions and Outlook -- References -- A Privacy-Preserving Technique to Identify the Useful Content of Documents Owned by Multiple Institutes -- 1 Introduction -- 1.1 Background -- 1.2 Study Objective -- 2 Problem Setting -- 3 Proposed Method -- 3.1 Basic Concept -- 3.2 Proposed Method -- 4 Empirical Experiments -- 4.1 Preprocessing of the Feedback Documents -- 4.2 Methods -- 4.3 Results -- 5 Discussion and Conclusion -- References -- Information Seeking and Use -- An Empirical Analysis of Newcomers' Contributions to Software-Engineering Conferences -- 1 Introduction -- 2 Background and Related Work -- 3 Methodology -- 3.1 Goal and Research Questions -- 3.2 Data Collection -- 3.3 Data Analysis -- 4 Results and Discussion -- 4.1 [ro:newAuthors]RQ1: Proportion of Newcomers -- 4.2 [ro:dbrNewAuthors]RQ2: Double-Blind Reviewing -- 5 Threats to Validity -- 6 Conclusion -- References. ; Examining Digital Humanities Tools Used by Taiwanese Historians with the Digital Visitors and Residents Framework.
• Titolo autorizzato: Leveraging Generative Intelligence in Digital Libraries
• ISBN: 981-9980-85-2
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Lingua di pubblicazione: Inglese
• Record Nr.: 9910767540303321
• Lo trovi qui: Univ. Federico II
• Serie: Lecture notes in computer science ; ; Volume 14457.