Search results

This study aims to adopt a systematic review approach to examine the existing literature on law and LLMs.It involves analyzing and synthesizing relevant research papers, reports and scholarly articles that discuss the use of LLMs in the legal domain. The review encompasses various aspects, including an analysis of LLMs, legal natural language processing (NLP), model tuning techniques, data processing strategies and frameworks for addressing the challenges associated with legal question-and-answer (Q&A) systems. Additionally, the study explores potential applications and services that can benefit from the integration of LLMs in the field of intelligent justice.

This paper surveys the state-of-the-art research on law LLMs and their application in the field of intelligent justice. The study aims to identify the challenges associated with developing Q&A systems based on LLMs and explores potential directions for future research and development. The ultimate goal is to contribute to the advancement of intelligent justice by effectively leveraging LLMs.

To effectively apply a law LLM, systematic research on LLM, legal NLP and model adjustment technology is required.

This study contributes to the field of intelligent justice by providing a comprehensive review of the current state of research on law LLMs.

In times of crisis, such as the Covid-19 global pandemic, journalists who write about biomedical information must have the strategic aim to be clearly and easily understood by everyone. In this study, we assume that journalistic discourse could benefit from language redundancy to improve clarity and simplicity aimed at science popularization. The concept of language redundancy is theoretically discussed with the support of discourse analysis and information theory. The methodology adopted is a corpus-based qualitative approach. Two corpora samples with Brazilian Portuguese (BP) texts on Covid-19 were collected. One with texts from a monthly science digital magazine called Pesquisa FAPESP aimed at students and researchers for scientific information dissemination and the other with popular language texts from a news Portal G1 (Rede Globo) aimed at unspecified and/or non-specialized readers. The materials were filtered with two descriptors: “vaccine” and “test.” Preliminary analysis of examples from these materials revealed two categories of redundancy: paraphrastic and polysemic. Paraphrastic redundancy is based on concomitant language reformulation of words, sentences, text excerpts, or even larger units. Polysemic redundancy does not easily show material evidence, but is based on cognitively predictable semantic association in socio-cultural domains. Both kinds of redundancy contribute, each in their own way, to improving text readability for science popularization in Brazil.

In the COVID-19 era, sign language (SL) translation has gained attention in online learning, which evaluates the physical gestures of each student and bridges the communication gap between dysphonia and hearing people. The purpose of this paper is to devote the alignment between SL sequence and nature language sequence with high translation performance.

SL can be characterized as joint/bone location information in two-dimensional space over time, forming skeleton sequences. To encode joint, bone and their motion information, we propose a multistream hierarchy network (MHN) along with a vocab prediction network (VPN) and a joint network (JN) with the recurrent neural network transducer. The JN is used to concatenate the sequences encoded by the MHN and VPN and learn their sequence alignments.

We verify the effectiveness of the proposed approach and provide experimental results on three large-scale datasets, which show that translation accuracy is 94.96, 54.52, and 92.88 per cent, and the inference time is 18 and 1.7 times faster than listen-attend-spell network (LAS) and visual hierarchy to lexical sequence network (H2SNet) , respectively.

In this paper, we propose a novel framework that can fuse multimodal input (i.e. joint, bone and their motion stream) and align input streams with nature language. Moreover, the provided framework is improved by the different properties of MHN, VPN and JN. Experimental results on the three datasets demonstrate that our approaches outperform the state-of-the-art methods in terms of translation accuracy and speed.

The integration of social media and e-commerce has resulted in a rising phenomenon among individual content providers (ICPs), who used to offer free content, to provide consumers with paid content, such as online courses, Q&As or consultations. Despite the prevalence of ICPs’ content monetization, empirical research has rarely studied its underlying mechanism. This paper examines how the characteristics of free content contributed by ICPs on social media platforms influence their paid content sales, focusing on the perspective of human brand.

The empirical setting is an online knowledge exchange platform, where users are allowed to provide free content (e.g. answers) on the social media platform and launch paid content (e.g. lectures) on the e-commerce platform. A machine learning technique is employed to construct measures for the characteristics of free content, and fixed-effects estimation is presented to confirm which factors have a significant influence on the sales of paid content.

The empirical results show that the quality, diversity and expertness of free content have a significant positive impact on the sales of the ICP-paid content, with the brand popularity of ICP playing a mediating role.

This study is the first attempt to demystify the relationship between content contribution and ICPs’ content monetization from the perspective of human brand. The findings validate the effectiveness of the “Selling by Contribution” strategy and provide valuable insights for ICPs and social media platforms.

This paper investigates how two characteristics of language, abstractness vs concreteness and narrativity, influence user engagement in communication exercises on innovation targeted to the general audience. The proposed conceptual model suggests that innovation fits well with more abstract language because of the association of innovation with imagination and distal construal. Moreover, communication of innovation may benefit from greater adherence to the narrativity arc, that is, early staging, increasing plot progression and climax optimal point. These effects are moderated by content variety and emotional tone, respectively.

Based on a Latent Dirichlet allocation (LDA) application on a sample of 3225 TED Talks transcripts, the authors identify 287 TED Talks on innovation, and then applied econometric analyses to test the hypotheses on the effects of abstractness vs concreteness and narrativity on engagement, and on the moderation effects of content variety and emotional tone.

The authors found that abstractness (vs concreteness) and narrativity have positive effects on engagement. These two effects are stronger with higher content variety and more positive emotional tone, respectively.

This paper extends the literature on communication of innovation, linguistics and text analysis by evaluating the roles of abstractness vs concreteness and narrativity in shaping appreciation of innovation.

This paper reports conceptual and empirical analyses on innovation dissemination through a popular medium – TED Talks – and applies modern text analysis algorithms to test hypotheses on the effects of two pivotal dimensions of language on user engagement.

A clickbait is a deceptive headline designed to boost ad revenue without presenting closely relevant content. There are numerous negative repercussions of clickbait, such as causing viewers to feel tricked and unhappy, causing long-term confusion, and even attracting cyber criminals. Automatic detection algorithms for clickbait have been developed to address this issue. The fact that there is only one semantic representation for the same term and a limited dataset in Chinese is a need for the existing technologies for detecting clickbait. This study aims to solve the limitations of automated clickbait detection in the Chinese dataset.

This study combines both to train the model to capture the probable relationship between clickbait news headlines and news content. In addition, part-of-speech elements are used to generate the most appropriate semantic representation for clickbait detection, improving clickbait detection performance.

This research successfully compiled a dataset containing up to 20,896 Chinese clickbait news articles. This collection contains news headlines, articles, categories and supplementary metadata. The suggested context-aware clickbait detection (CA-CD) model outperforms existing clickbait detection approaches on many criteria, demonstrating the proposed strategy's efficacy.

The originality of this study resides in the newly compiled Chinese clickbait dataset and contextual semantic representation-based clickbait detection approach employing transfer learning. This method can modify the semantic representation of each word based on context and assist the model in more precisely interpreting the original meaning of news articles.

Although numerous signal modalities are available for emotion recognition, audio and visual modalities are the most common and predominant forms for human beings to express their emotional states in daily communication. Therefore, how to achieve automatic and accurate audiovisual emotion recognition is significantly important for developing engaging and empathetic human–computer interaction environment. However, two major challenges exist in the field of audiovisual emotion recognition: (1) how to effectively capture representations of each single modality and eliminate redundant features and (2) how to efficiently integrate information from these two modalities to generate discriminative representations.

A novel key-frame extraction-based attention fusion network (KE-AFN) is proposed for audiovisual emotion recognition. KE-AFN attempts to integrate key-frame extraction with multimodal interaction and fusion to enhance audiovisual representations and reduce redundant computation, filling the research gaps of existing approaches. Specifically, the local maximum–based content analysis is designed to extract key-frames from videos for the purpose of eliminating data redundancy. Two modules, including “Multi-head Attention-based Intra-modality Interaction Module” and “Multi-head Attention-based Cross-modality Interaction Module”, are proposed to mine and capture intra- and cross-modality interactions for further reducing data redundancy and producing more powerful multimodal representations.

Extensive experiments on two benchmark datasets (i.e. RAVDESS and CMU-MOSEI) demonstrate the effectiveness and rationality of KE-AFN. Specifically, (1) KE-AFN is superior to state-of-the-art baselines for audiovisual emotion recognition. (2) Exploring the supplementary and complementary information of different modalities can provide more emotional clues for better emotion recognition. (3) The proposed key-frame extraction strategy can enhance the performance by more than 2.79 per cent on accuracy. (4) Both exploring intra- and cross-modality interactions and employing attention-based audiovisual fusion can lead to better prediction performance.

The proposed KE-AFN can support the development of engaging and empathetic human–computer interaction environment.

Sarcasm is a linguistic expression that usually carries the opposite meaning of what is being said by words, thus making it difficult for machines to discover the actual meaning. It is mainly distinguished by the inflection with which it is spoken, with an undercurrent of irony, and is largely dependent on context, which makes it a difficult task for computational analysis. Moreover, sarcasm expresses negative sentiments using positive words, allowing it to easily confuse sentiment analysis models. This paper aims to demonstrate the task of sarcasm detection using the approach of machine and deep learning.

For the purpose of sarcasm detection, machine and deep learning models were used on a data set consisting of 1.3 million social media comments, including both sarcastic and non-sarcastic comments. The data set was pre-processed using natural language processing methods, and additional features were extracted and analysed. Several machine learning models, including logistic regression, ridge regression, linear support vector and support vector machines, along with two deep learning models based on bidirectional long short-term memory and one bidirectional encoder representations from transformers (BERT)-based model, were implemented, evaluated and compared.

The performance of machine and deep learning models was compared in the task of sarcasm detection, and possible ways of improvement were discussed. Deep learning models showed more promise, performance-wise, for this type of task. Specifically, a state-of-the-art model in natural language processing, namely, BERT-based model, outperformed other machine and deep learning models.

This study compared the performance of the various machine and deep learning models in the task of sarcasm detection using the data set of 1.3 million comments from social media.

Wine tourism is gaining increasing popularity among Chinese tourists, making it necessary to thoroughly examine tourist behavior. While online reviews posted by wine tourists have been extensively studied from the perspectives of destinations and wineries, the perspective of the tourists themselves has been overlooked. To address this gap, this study aims to identify significant attributes intrinsic to the tourism experiences of Chinese wine tourists by adopting a text-mining approach from a tourist-centric perspective.

The authors use topic modeling to extract these attributes, calculate topic intensity to understand tourists’ attention distribution across these attributes and conduct topical sentiment analysis to evaluate tourists’ satisfaction levels with each attribute. The authors perform importance-performance analyses (IPAs) using topic intensity and sentiment scores. Furthermore, the authors conduct semistructured in-depth interviews with Chinese wine tourists to gain insights into the underlying reasons behind the key findings.

The study identifies eleven attributes for domestic wine tourists and seven attributes for outbound wine tourists. From the reviews of both domestic and outbound tourists, three common attributes have been identified: “scenic view”, “wine tasting and purchase” and “wine knowledge”.

According to the results of the IPAs, there is a pressing need for enhancements in the wine tasting and purchasing experience at domestic wine attractions. Additionally, managers of domestic wine attractions should continue to prioritize the positive aspects of the family trip experience and scenic views. On the other hand, for outbound wine attractions, it is crucial for managers to maintain their efforts in providing opportunities for wine knowledge acquisition, ensuring scenic views and upholding the reputation of wine regions.

First, this study breaks new ground by adopting a tourist-centric perspective to extract significant attributes from real wine tourism reviews. Second, the authors conduct a comparative analysis between Chinese wine tourists who travel domestically and those who travel abroad. The third novel aspect of this study is the application of IPA based on textual review data in the context of wine tourism. Fourth, by integrating topic modeling with qualitative interviews, the authors use a mixed-method approach to gain deeper insights into the experiences of Chinese wine tourists.

This study aims to construct a sentiment series generation method for danmu comments based on deep learning, and explore the features of sentiment series after clustering.

This study consisted of two main parts: danmu comment sentiment series generation and clustering. In the first part, the authors proposed a sentiment classification model based on BERT fine-tuning to quantify danmu comment sentiment polarity. To smooth the sentiment series, they used methods, such as comprehensive weights. In the second part, the shaped-based distance (SBD)-K-shape method was used to cluster the actual collected data.

The filtered sentiment series or curves of the microfilms on the Bilibili website could be divided into four major categories. There is an apparently stable time interval for the first three types of sentiment curves, while the fourth type of sentiment curve shows a clear trend of fluctuation in general. In addition, it was found that “disputed points” or “highlights” are likely to appear at the beginning and the climax of films, resulting in significant changes in the sentiment curves. The clustering results show a significant difference in user participation, with the second type prevailing over others.

Their sentiment classification model based on BERT fine-tuning outperformed the traditional sentiment lexicon method, which provides a reference for using deep learning as well as transfer learning for danmu comment sentiment analysis. The BERT fine-tuning–SBD-K-shape algorithm can weaken the effect of non-regular noise and temporal phase shift of danmu text.