Search results

Question answering (QA) answers the questions asked by people in the form of natural language. In the QA, due to the subjectivity of users, the questions they query have different expressions, which increases the difficulty of text retrieval. Therefore, the purpose of this paper is to explore new query rewriting method for QA that integrates multiple related questions (RQs) to form an optimal question. Moreover, it is important to generate a new dataset of the original query (OQ) with multiple RQs.

This study collects a new dataset SQuAD_extend by crawling the QA community and uses word-graph to model the collected OQs. Next, Beam search finds the best path to get the best question. To deeply represent the features of the question, pretrained model BERT is used to model sentences.

The experimental results show three outstanding findings. (1) The quality of the answers is better after adding the RQs of the OQs. (2) The word-graph that is used to model the problem and choose the optimal path is conducive to finding the best question. (3) Finally, BERT can deeply characterize the semantics of the exact problem.

The proposed method can use word-graph to construct multiple questions and select the optimal path for rewriting the question, and the quality of answers is better than the baseline. In practice, the research results can help guide users to clarify their query intentions and finally achieve the best answer.

In the era of mobile internet, the social Q&A community has built a large-scale and complex knowledge label network through its internal knowledge units, and the scale and structure of the network have changed over time. By analysing the structural characteristics and evolution rules of knowledge label networks, the main purpose of this study is to understand the internal mechanisms of the replacement of old and new knowledge and the expansion of knowledge element boundaries, so as to explore the realization path of knowledge management in the new era from the perspective of complex networks.

This paper uses distributed crawlers to capture 419,349 samples from the Zhihu platform. Each sample contains 33 characteristic dimensions, and the natural year is used as the sliding window to divide the whole. In this study, the global knowledge label network and 11 local knowledge label networks are first constructed. Then, the degree distribution analysis and central node exploration of the knowledge label network are carried out using the complex network method. Finally, the average shortest path and average clustering coefficient of the network are analysed by the time series method, and the ARIMA model is used to predict the evolution of the correlation coefficient.

The research results show that the dissimilation degree of the degree distribution of the knowledge label network has gradually decreased from 2011 to 2021, and the attention of users in the knowledge community has shown a trend of distraction and diversification over time. With the expansion of the scale of the knowledge label network and the transformation to an information network, the network sparsity is becoming more and more obvious, and the knowledge granularity of the Q&A community is being refined and diversified. The prediction of the correlation coefficient of the knowledge label network by the ARIMA model shows that the connection between the labels is lacking diversity and the opinion strengthening phenomenon tends to strengthen, which is more likely to form the “echo chamber effect”, resulting in mutual isolation and even opposition between different circles. The Q&A community is about to enter a mature stage, and the corresponding status of each label has been finalized. The future development trend of label networks will be reflected in the substitution between labels, and the specific structure will not change significantly.

The Q&A community model is the trend in Web 2.0 community development. This study proves the effectiveness of complex networks and time series prediction methods in knowledge label network mining in the Q&A community.

As academic social Q&A networking websites become more popular, scholars are increasingly using them to meet their information needs by asking academic questions. However, compared with other types of social media, scholars are less active on these sites, resulting in a lower response quantity for some questions. This paper explores the factors that help explain how to ask questions that generate more responses and examines the impact of different disciplines on response quantity.

The study examines 1,968 questions in five disciplines on the academic social Q&A platform ResearchGate Q&A and explores how the linguistic characteristics of these questions affect the number of responses. It uses a range of methods to statistically analyze the relationship between these linguistic characteristics and the number of responses, and conducts comparisons between disciplines.

The findings indicate that some linguistic characteristics, such as sadness, positive emotion and second-person pronouns, have a positive effect on response quantity; conversely, a high level of function words and first-person pronouns has a negative effect. However, the impacts of these linguistic characteristics vary across disciplines.

This study provides support for academic social Q&A platforms to assist scholars in asking richer questions that are likely to generate more answers across disciplines, thereby promoting improved academic communication among scholars.

Online health question-and-answer (Q&A) forums have developed a new business model whereby listeners (peer patients) can pay to read health information derived from consultations between askers (focal patients) and answerers (physicians). However, research exploring the mechanism behind peer patients' purchase decisions and the specific nature of the information driving these decisions has remained limited. This study aims to develop a theoretical model for understanding how peer patients make such decisions based on limited information, i.e. the first question displayed in each focal patient-physician interaction record, considering argument quality (interrogative form and information details) and source credibility (patient experience of focal patients), including the contingent role of urgency.

The model was tested by text mining 1,960 consultation records from a popular Chinese online health Q&A forum on the Yilu App. These records involved interactions between focal patients and physicians and were purchased by 447,718 peer patients seeking health-related information until this research.

Patient experience embedded in focal patients' questions plays a significant role in inducing peer patients to purchase previous consultation records featuring exchanges between focal patients and physicians; in particular, increasingly detailed information is associated with a reduced probability of making a purchase. When focal patients demonstrate a high level of urgency, the effect of information details is weakened, while the interrogative form is strengthened.

The originality of this study lies in its exploration of the monetization mechanism forming the trilateral relationship between askers (focal patients), answerers (physicians) and listeners (peer patients) in the business model “paying to view others' answers” in the online health Q&A forum and the moderating role of urgency in explaining the mechanism of how first questions influence peer patients' purchasing behavior.

Intent detection and slot filling are two important tasks in question comprehension of a question answering system. This study aims to build a joint task model with some generalization ability and benchmark its performance over other neural network models mentioned in this paper.

This study used a deep-learning-based approach for the joint modeling of question intent detection and slot filling. Meanwhile, the internal cell structure of the long short-term memory (LSTM) network was improved. Furthermore, the dataset Computer Science Literature Question (CSLQ) was constructed based on the Science and Technology Knowledge Graph. The datasets Airline Travel Information Systems, Snips (a natural language processing dataset of the consumer intent engine collected by Snips) and CSLQ were used for the empirical analysis. The accuracy of intent detection and F1 score of slot filling, as well as the semantic accuracy of sentences, were compared for several models.

The results showed that the proposed model outperformed all other benchmark methods, especially for the CSLQ dataset. This proves that the design of this study improved the comprehensive performance and generalization ability of the model to some extent.

This study contributes to the understanding of question sentences in a specific domain. LSTM was improved, and a computer literature domain dataset was constructed herein. This will lay the data and model foundation for the future construction of a computer literature question answering system.

The purpose of this study is to identify the research fronts by analysing highly cited core papers adjusted with the age of a paper in library and information science (LIS) where natural language processing (NLP) is being applied significantly.

By excavating international databases, 3,087 core papers that received at least 5% of the total citations have been identified. By calculating the average mean years of these core papers, and total citations received, a CPT (citation/publication/time) value was calculated in all 20 fronts to understand how a front is relatively receiving greater attention among peers within a course of time. One theme article has been finally identified from each of these 20 fronts.

Bidirectional encoder representations from transformers with CPT value 1.608 followed by sentiment analysis with CPT 1.292 received highest attention in NLP research. Columbia University New York, in terms of University, Journal of the American Medical Informatics Association, in terms of journals, USA followed by People Republic of China, in terms of country and Xu, H., University of Texas, in terms of author are the top in these fronts. It is identified that the NLP applications boost the performance of digital libraries and automated library systems in the digital environment.

Any research fronts that are identified in the findings of this paper may be used as a base for researchers who intended to perform extensive research on NLP.

To the best of the authors’ knowledge, the methodology adopted in this paper is the first of its kind where meta-analysis approach has been used for understanding the research fronts in sub field like NLP for a broad domain like LIS.

Automatically extracting stance information from natural language texts is a significant research problem with various applications, particularly after the recent explosion of data on the internet via platforms like social media sites. Stance detection system helps determine whether the author agree, against or has a neutral opinion with the given target. Most of the research in stance detection focuses on the English language, while few research was conducted on the Arabic language.

This paper aimed to address stance detection on Arabic tweets by building and comparing different stance detection models using four transformers, namely: Araelectra, MARBERT, AraBERT and Qarib. Using different weights for these transformers, the authors performed extensive experiments fine-tuning the task of stance detection Arabic tweets with the four different transformers.

The results showed that the AraBERT model learned better than the other three models with a 70% F1 score followed by the Qarib model with a 68% F1 score.

A limitation of this study is the imbalanced dataset and the limited availability of annotated datasets of SD in Arabic.

Provide comprehensive overview of the current resources for stance detection in the literature, including datasets and machine learning methods used. Therefore, the authors examined the models to analyze and comprehend the obtained findings in order to make recommendations for the best performance models for the stance detection task.

This paper aims to provide an overview of key definitions related to ChatGPT, a public tool developed by OpenAI, and its underlying technology, Generative Pretrained Transformer (GPT).

This paper includes an interview with ChatGPT on its potential impact on academia and libraries. The interview discusses the benefits of ChatGPT such as improving search and discovery, reference and information services; cataloging and metadata generation; and content creation, as well as the ethical considerations that need to be taken into account, such as privacy and bias.

ChatGPT has considerable power to advance academia and librarianship in both anxiety-provoking and exciting new ways. However, it is important to consider how to use this technology responsibly and ethically, and to uncover how we, as professionals, can work alongside this technology to improve our work, rather than to abuse it or allow it to abuse us in the race to create new scholarly knowledge and educate future professionals.

This paper discusses the history and technology of GPT, including its generative pretrained transformer model, its ability to perform a wide range of language-based tasks and how ChatGPT uses this technology to function as a sophisticated chatbot.

The current study aims to investigate the factors that impact the feedback received on answers to questions in social Q&A communities and whether the expertise-required question influences the role of these factors on the feedback.

To understand the antecedents and consequences that influence the feedback received on answers to online community questions, the elaboration likelihood model (ELM) is applied in this study. The authors use web data crawling methods and a combination of quantitative analyses. The data for this study came from Zhihu; in total, 353,775 responses were obtained to 1,531 questions, ranging from 49 to 23,681 responses per question. Each answer received 0 to 113,892 likes and 0 to 6,250 comments.

The answers' cognitive and emotional components and the answerer's influence positively affect user feedback behavior. In addition, the expertise-required question moderates the effects of the answer's cognitive component and emotional component on the user feedback, moderating the effects of the answerer's influence on the user approval feedback.

This study builds upon a limited yet growing body of literature on a theme of great relevance to scholars, practitioners and social media users concerning the effects of the connotation of answers (i.e. their cognitive and emotional components) and the answerer's influence on user feedback (i.e. approval and collaborative feedback) in social Q&A communities. The authors further consider the moderating role of the domain expertise required by the question (expertise-required question). The ELM model is applied to explore the relationships between questions, answers and feedback. The findings of this study add a new perspective to the research on user feedback and have implications for the management of social Q&A communities.

Seekers who visit professional virtual communities (PVCs) are usually motivated by knowledge-seeking, which is a complex cognitive process. How do seekers search for knowledge, and how is their search linked to prior knowledge or PVC situation factors? From the cognitive process and interactional psychology perspectives, this study investigated the three-way interactions between seekers’ expertise, task complexity, and perceptions of PVC features (i.e. knowledge quality and system quality) on knowledge-seeking strategies and resultant outcomes.

A field experiment was conducted with 119 seekers in a PVC using a 2 × 2 factorial design of seekers’ expertise (i.e. expert versus novice) and task complexity (i.e. low versus high).

The study reveals three significant insights: (1) For a high-complexity task, experts adopt an ask-directed searching strategy compared to novices, whereas novices adopt a browsing strategy; (2) For a high-complexity task, experts who perceive a high system quality are more likely than novices to adopt an ask-directed searching strategy; and (3) Task completion time and task quality are associated with the adoption of ask-directed searching strategies, whereas knowledge seekers’ satisfaction is more associated with the adoption of browsing strategy.

We draw on the perspectives of cognitive process and interactional psychology to explore potential two- and three-way interactions of seekers’ expertise, task complexity, and PVC features on the adoption of knowledge-seeking strategies in a PVC context. Our findings provide deep insights into seekers’ behavior in a PVC, given the popularity of the search for knowledge in PVCs.