Search results

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.

With the increasing number of Web services, correct and efficient classification of Web services is crucial to improve the efficiency of service discovery. However, existing Web service classification approaches ignore the class overlap in Web services, resulting in poor accuracy of classification in practice. This paper aims to provide an approach to address this issue.

This paper proposes a label confusion and priori correction-based Web service classification approach. First, functional semantic representations of Web services descriptions are obtained based on BERT. Then, the ability of the model is enhanced to recognize and classify overlapping instances by using label confusion learning techniques; Finally, the predictive results are corrected based on the label prior distribution to further improve service classification effectiveness.

Experiments based on the ProgrammableWeb data set show that the proposed model demonstrates 4.3%, 3.2% and 1% improvement in Macro-F1 value compared to the ServeNet-BERT, BERT-DPCNN and CARL-NET, respectively.

This paper proposes a Web service classification approach for the overlapping categories of Web services and improve the accuracy of Web services classification.

Safety management plays an important part in coal mine construction. Due to complex data, the implementation of the construction safety knowledge scattered in standards poses a challenge. This paper aims to develop a knowledge extraction model to automatically and efficiently extract domain knowledge from unstructured texts.

Bidirectional encoder representations from transformers (BERT)-bidirectional long short-term memory (BiLSTM)-conditional random field (CRF) method based on a pre-training language model was applied to carry out knowledge entity recognition in the field of coal mine construction safety in this paper. Firstly, 80 safety standards for coal mine construction were collected, sorted out and marked as a descriptive corpus. Then, the BERT pre-training language model was used to obtain dynamic word vectors. Finally, the BiLSTM-CRF model concluded the entity’s optimal tag sequence.

Accordingly, 11,933 entities and 2,051 relationships in the standard specifications texts of this paper were identified and a language model suitable for coal mine construction safety management was proposed. The experiments showed that F1 values were all above 60% in nine types of entities such as security management. F1 value of this model was more than 60% for entity extraction. The model identified and extracted entities more accurately than conventional methods.

This work completed the domain knowledge query and built a Q&A platform via entities and relationships identified by the standard specifications suitable for coal mines. This paper proposed a systematic framework for texts in coal mine construction safety to improve efficiency and accuracy of domain-specific entity extraction. In addition, the pretraining language model was also introduced into the coal mine construction safety to realize dynamic entity recognition, which provides technical support and theoretical reference for the optimization of safety management platforms.

The number of construction dispute cases has maintained a high growth trend in recent years. The effective exploration and management of construction contract risk can directly promote the overall performance of the project life cycle. The miss of clauses may result in a failure to match with standard contracts. If the contract, modified by the owner, omits key clauses, potential disputes may lead to contractors paying substantial compensation. Therefore, the identification of construction project contract missing clauses has heavily relied on the manual review technique, which is inefficient and highly restricted by personnel experience. The existing intelligent means only work for the contract query and storage. It is urgent to raise the level of intelligence for contract clause management. Therefore, this paper aims to propose an intelligent method to detect construction project contract missing clauses based on Natural Language Processing (NLP) and deep learning technology.

A complete classification scheme of contract clauses is designed based on NLP. First, construction contract texts are pre-processed and converted from unstructured natural language into structured digital vector form. Following the initial categorization, a multi-label classification of long text construction contract clauses is designed to preliminary identify whether the clause labels are missing. After the multi-label clause missing detection, the authors implement a clause similarity algorithm by creatively integrating the image detection thought, MatchPyramid model, with BERT to identify missing substantial content in the contract clauses.

1,322 construction project contracts were tested. Results showed that the accuracy of multi-label classification could reach 93%, the accuracy of similarity matching can reach 83%, and the recall rate and F1 mean of both can reach more than 0.7. The experimental results verify the feasibility of intelligently detecting contract risk through the NLP-based method to some extent.

NLP is adept at recognizing textual content and has shown promising results in some contract processing applications. However, the mostly used approaches of its utilization for risk detection in construction contract clauses predominantly are rule-based, which encounter challenges when handling intricate and lengthy engineering contracts. This paper introduces an NLP technique based on deep learning which reduces manual intervention and can autonomously identify and tag types of contractual deficiencies, aligning with the evolving complexities anticipated in future construction contracts. Moreover, this method achieves the recognition of extended contract clause texts. Ultimately, this approach boasts versatility; users simply need to adjust parameters such as segmentation based on language categories to detect omissions in contract clauses of diverse languages.

The research on structure function recognition mainly concentrates on identifying a specific part of academic literature and its applicability in the multidiscipline perspective. A specific part of academic literature, such as sentences, paragraphs and chapter contents are also called a level of academic literature in this paper. There are a few comparative research works on the relationship between models, disciplines and levels in the process of structure function recognition. In view of this, comparative research on structure function recognition based on deep learning has been conducted in this paper.

An experimental corpus, including the academic literature of traditional Chinese medicine, library and information science, computer science, environmental science and phytology, was constructed. Meanwhile, deep learning models such as convolutional neural networks (CNN), long and short-term memory (LSTM) and bidirectional encoder representation from transformers (BERT) were used. The comparative experiments of structure function recognition were conducted with the help of the deep learning models from the multilevel perspective.

The experimental results showed that (1) the BERT model performed best, with F1 values of 78.02, 89.41 and 94.88%, respectively at the level of sentence, paragraph and chapter content. (2) The deep learning models performed better on the academic literature of traditional Chinese medicine than on other disciplines in most cases, e.g. F1 values of CNN, LSTM and BERT, respectively arrived at 71.14, 69.96 and 78.02% at the level of sentence. (3) The deep learning models performed better at the level of chapter content than other levels, the maximum F1 values of CNN, LSTM and BERT at 91.92, 74.90 and 94.88%, respectively. Furthermore, the confusion matrix of recognition results on the academic literature was introduced to find out the reason for misrecognition.

This paper may inspire other research on structure function recognition, and provide a valuable reference for the analysis of influencing factors.

Intent detection (ID) and slot filling (SF) are two important tasks in natural language understanding. ID is to identify the main intent of a paragraph of text. The goal of SF is to extract the information that is important to the intent from the input sentence. However, most of the existing methods use sentence-level intention recognition, which has the risk of error propagation, and the relationship between intention recognition and SF is not explicitly modeled. Aiming at this problem, this paper proposes a collaborative model of ID and SF for intelligent spoken language understanding called ID-SF-Fusion.

ID-SF-Fusion uses Bidirectional Encoder Representation from Transformers (BERT) and Bidirectional Long Short-Term Memory (BiLSTM) to extract effective word embedding and context vectors containing the whole sentence information respectively. Fusion layer is used to provide intent–slot fusion information for SF task. In this way, the relationship between ID and SF task is fully explicitly modeled. This layer takes the result of ID and slot context vectors as input to obtain the fusion information which contains both ID result and slot information. Meanwhile, to further reduce error propagation, we use word-level ID for the ID-SF-Fusion model. Finally, two tasks of ID and SF are realized by joint optimization training.

We conducted experiments on two public datasets, Airline Travel Information Systems (ATIS) and Snips. The results show that the Intent ACC score and Slot F1 score of ID-SF-Fusion on ATIS and Snips are 98.0 per cent and 95.8 per cent, respectively, and the two indicators on Snips dataset are 98.6 per cent and 96.7 per cent, respectively. These models are superior to slot-gated, SF-ID NetWork, stack-Prop and other models. In addition, ablation experiments were performed to further analyze and discuss the proposed model.

This paper uses word-level intent recognition and introduces intent information into the SF process, which is a significant improvement on both data sets.

Online medical repositories provide a platform for users to share information and dynamically access abundant electronic health data. It is important to determine whether case report information can assist the general public in appropriately managing their diseases. Therefore, this paper aims to introduce a novel deep learning-based method that allows non-professionals to make inquiries using ordinary vocabulary, retrieving the most relevant case reports for accurate and effective health information.

The dataset of case reports was collected from both the patient-generated research network and the digital medical journal repository. To enhance the accuracy of obtaining relevant case reports, the authors propose a retrieval approach that combines BERT and BiLSTM methods. The authors identified representative health-related case reports and analyzed the retrieval performance, as well as user judgments.

This study aims to provide the necessary functionalities to deliver relevant health case reports based on input from ordinary terms. The proposed framework includes features for health management, user feedback acquisition and ranking by weights to obtain the most pertinent case reports.

This study contributes to health information systems by analyzing patients' experiences and treatments with the case report retrieval model. The results of this study can provide immense benefit to the general public who intend to find treatment decisions and experiences from relevant case reports.

Genre classification of songs based on lyrics is a challenging task even for humans, however, state-of-the-art natural language processing has recently offered advanced solutions to this task. The purpose of this study is to advance the understanding and application of natural language processing and deep learning in the domain of music genre classification, while also contributing to the broader themes of global knowledge and communication, and sustainable preservation of cultural heritage.

The main contribution of this study is the development and evaluation of various machine and deep learning models for song genre classification. Additionally, we investigated the effect of different word embeddings, including Global Vectors for Word Representation (GloVe) and Word2Vec, on the classification performance. The tested models range from benchmarks such as logistic regression, support vector machine and random forest, to more complex neural network architectures and transformer-based models, such as recurrent neural network, long short-term memory, bidirectional long short-term memory and bidirectional encoder representations from transformers (BERT).

The authors conducted experiments on both English and multilingual data sets for genre classification. The results show that the BERT model achieved the best accuracy on the English data set, whereas cross-lingual language model pretraining based on RoBERTa (XLM-RoBERTa) performed the best on the multilingual data set. This study found that songs in the metal genre were the most accurately labeled, as their text style and topics were the most distinct from other genres. On the contrary, songs from the pop and rock genres were more challenging to differentiate. This study also compared the impact of different word embeddings on the classification task and found that models with GloVe word embeddings outperformed Word2Vec and the learning embedding layer.

This study presents the implementation, testing and comparison of various machine and deep learning models for genre classification. The results demonstrate that transformer models, including BERT, robustly optimized BERT pretraining approach, distilled bidirectional encoder representations from transformers, bidirectional and auto-regressive transformers and XLM-RoBERTa, outperformed other models.

Tourists with different cultural backgrounds think and behave differently. Accurately capturing and correctly understanding cultural differences will help tourist destinations in product/service planning, marketing communication and attracting and retaining tourists. This research employs Hofstede's cultural dimensions theory to analyse the variations in destination image perceptions of Chinese-speaking and English-speaking tourists to Xiamen, a prominent tourist attraction in China.

The evaluation utilizes a two-stage approach, incorporating LDA and BERT-BILSTM models. By leveraging text mining, sentiment analysis and t-tests, this research investigates the variations in tourists' perceptions of Xiamen across different cultures.

The results reveal that cultural disparities significantly impact tourists' perceived image of Xiamen, particularly regarding their preferences for renowned tourist destinations and the factors influencing their travel experience.

This research pioneers applying natural language processing methods and machine learning techniques to affirm the substantial differences in the perceptions of tourist destinations among Chinese-speaking and English-speaking tourists based on Hofstede's cultural theory. The findings furnish theoretical insights for destination marketing organizations to target diverse cultural tourists through precise marketing strategies and illuminate the practical application of Hofstede's cultural theory in tourism and hospitality.

This study aims to establish a model for rapid and accurate emotion recognition in restaurant online reviews, thus advancing the literature and providing practical insights into electronic word-of-mouth management for the industry.

This study elaborates a hybrid model that integrates deep learning (DL) and a sentiment lexicon (SL) and compares it to five other models, including SL, random forest (RF), naïve Bayes, support vector machine (SVM) and a DL model, for the task of emotion recognition in restaurant online reviews. These models are trained and tested using 652,348 online reviews from 548 restaurants.

The hybrid approach performs well for valence-based emotion and discrete emotion recognition and is highly applicable for mining online reviews in a restaurant setting. The performances of SL and RF are inferior when it comes to recognizing discrete emotions. The DL method and SVM can perform satisfactorily in the valence-based emotion recognition.

These findings provide methodological and theoretical implications; thus, they advance the current state of knowledge on emotion recognition in restaurant online reviews. The results also provide practical insights into intelligent service quality monitoring and electronic word-of-mouth management for the industry.

This study proposes a superior model for emotion recognition in restaurant online reviews. The methodological framework and steps are elucidated in detail for future research and practical application. This study also details the performances of other commonly used models to support the selection of methods in research and practical applications.