Development and multicenter validation of chest X-ray radiography interpretations based on natural language processing

BackgroundIt is essential for radiologists to communicate actionable findings to the referring clinicians reliably. Natural language processing (NLP) has been shown to help identify free-text radiology reports including actionable findings. However, the application of recent deep learning techniques to radiology reports, which can improve the detection performance, has not been thoroughly examined. Moreover, free-text that clinicians input in the ordering form (order information) has seldom been used to identify actionable reports. This study aims to evaluate the benefits of two new approaches: (1) bidirectional encoder representations from transformers (BERT), a recent deep learning architecture in NLP, and (2) using order information in addition to radiology reports.MethodsWe performed a binary classification to distinguish actionable reports (i.e., radiology reports tagged as actionable in actual radiological practice) from non-actionable ones (those without an actionable tag). 90,923 Japanese radiology reports in our hospital were used, of which 788 (0.87%) were actionable. We evaluated four methods, statistical machine learning with logistic regression (LR) and with gradient boosting decision tree (GBDT), and deep learning with a bidirectional long short-term memory (LSTM) model and a publicly available Japanese BERT model. Each method was used with two different inputs, radiology reports alone and pairs of order information and radiology reports. Thus, eight experiments were conducted to examine the performance.ResultsWithout order information, BERT achieved the highest area under the precision-recall curve (AUPRC) of 0.5138, which showed a statistically significant improvement over LR, GBDT, and LSTM, and the highest area under the receiver operating characteristic curve (AUROC) of 0.9516. Simply coupling the order information with the radiology reports slightly increased the AUPRC of BERT but did not lead to a statistically significant improvement. This may be due to the complexity of clinical decisions made by radiologists.ConclusionsBERT was assumed to be useful to detect actionable reports. More sophisticated methods are required to use order information effectively.

With the continuous evolution of natural language processing (NLP), conversational agents have become pivotal in enhancing user engagement and satisfaction in the e-commerce domain. This paper presents a comprehensive study and implementation of intent recognition and slot filling techniques tailored for an e-commerce chatbot. Leveraging a dataset of 8,000 samples, we employed a Convolutional Neural Network (CNN) combined with Long Short-Term Memory (LSTM) networks for intent recognition, achieving an accuracy of 87%. For slot filling, we utilized the Bidirectional Encoder Representations from Transformers (BERT) model, also attaining an accuracy of 87%. The chatbot seamlessly integrates with an e-commerce database, using OpenAI's GPT-3 to generate natural language responses from query results. Our system demonstrates significant advancements in processing user queries, generating precise database queries, and providing coherent and relevant responses, thereby enhancing the overall user experience. This work aims to equip researchers and practitioners with insights into the methodologies and challenges in developing sophisticated e-commerce chatbots, fostering further innovation in this field. Key Words: Intent Recognition, Slot Filling, Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Bidirectional Encoder Representations from Transformers (BERT), GPT-3, Natural Language Understanding (NLU), Chatbot

To address the insufficient expressive capabilities of traditional methods in assessing the development level of rural tourism, this study explores the fusion application of the Bidirectional Encoder Representations from Transformers (BERT) and the Back Propagation (BP) algorithm to enhance the accuracy and comprehensiveness of rural tourism development assessment. Firstly, this study introduces the BERT deep learning model and its applications in natural language processing, alongside the role of the BP algorithm in pattern recognition and predictive analysis. Subsequently, a framework for assessing rural tourism development levels, integrating BERT and the BP algorithm, is proposed. This framework collects multidimensional rural tourism-related data and utilizes the BERT model for sentiment analysis and topic extraction from textual data. Empirical analysis of rural tourism development in a specific region validates the effectiveness of the proposed approach. Experimental results demonstrate: (1) The model achieves an accuracy of 84.33% and an F1 score of 85.33% on the publicly available Laptop dataset, with a processing time of 20 s, significantly outperforming other methods. Compared to traditional approaches, the proposed method accurately captures correlations between textual information and numerical data, thereby enhancing the credibility and accuracy of assessment results. (2) From the ablation study results, it is evident that removing any component from the model leads to performance degradation. Specifically, removing the Bidirectional Gated Recurrent Unit (BiGRU) reduces accuracy and F1 scores to 78.21% and 76.33% on the Laptop dataset, and to 85.10% and 70.45% on the Tourist_F dataset. Removing Text Convolutional Neural Network (CNN) reduces accuracy and F1 scores to 79.34% and 77.56% on the Laptop dataset, and to 86.25% and 72.11% on the Tourist_F dataset. The most significant performance decline occurs upon removing BERT, with accuracy and F1 scores decreasing to 70.14% and 66.43% on the Laptop dataset, and to 78.45% and 60.33% on the Tourist_F dataset. These results indicate that BiGcRU, TextCNN, and BERT each contribute significantly to the model’s performance. This study provides substantial support for advancing sustainable development in rural tourism, offering significant practical and innovative value.

Sentiment analysis (SA) detects people’s opinions from text engaging natural language processing (NLP) techniques. Recent research has shown that deep learning models, i.e., Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Transformer-based provide promising results for recognizing sentiment. Nonetheless, CNN has the advantage of extracting high-level features by using convolutional and max-pooling layers; it cannot efficiently learn a sequence of correlations. At the same time, Bidirectional RNN uses two RNN directions to improve extracting long-term dependencies. However, it cannot extract local features in parallel, and Transformer-based like Bidirectional Encoder Representations from Transformers (BERT) are the computational resources needed to fine-tune, facing an overfitting problem on small datasets. This paper proposes a novel attention-based model that utilizes CNNs with LSTM (named ACL-SA). First, it applies a preprocessor to enhance the data quality and employ term frequency-inverse document frequency (TF-IDF) feature weighting and pre-trained Glove word embedding approaches to extract meaningful information from textual data. In addition, it utilizes CNN’s max-pooling to extract contextual features and reduce feature dimensionality. Moreover, it uses an integrated bidirectional LSTM to capture long-term dependencies. Furthermore, it applies the attention mechanism at the CNN’s output layer to emphasize each word’s attention level. To avoid overfitting, the Guasiannoise and GuasianDroupout are adopted as regularization. The model’s robustness is evaluated on four English standard datasets, i.e., Sentiment140, US-airline, Sentiment140-MV, SA4A with various performance matrices, and compared efficiency with existing baseline models and approaches. The experiment results show that the proposed method significantly outperforms the state-of-the-art models.

With the increasing number of web texts, the classification of web texts has become an important task. In this paper, the text word vector representation method is first analyzed, and bidirectional encoder representations from transformers (BERT) are selected to extract the word vector. The bidirectional gated recurrent unit (BiGRU), convolutional neural network (CNN), and attention mechanism are combined to obtain the context and local features of the text, respectively. Experiments were carried out using the THUCNews dataset. The results showed that in the comparison between word-to-vector (Word2vec), Glove, and BERT, the BERT obtained the best classification result. In the classification of different types of text, the average accuracy and F1 value of the BERT-BGCA method reached 0.9521 and 0.9436, respectively, which were superior to other deep learning methods such as TextCNN. The results suggest that the BERT-BGCA method is effective in classifying web texts and can be applied in practice.

Short text classification is a research focus for natural language processing (NLP), which is widely used in news classification, sentiment analysis, mail filtering and other fields. In recent years, deep learning techniques are applied to text classification and has made some progress. Different from ordinary text classification, short text has the problem of less vocabulary and feature sparsity, which raise higher request for text semantic feature representation. To address this issue, this paper propose a feature fusion framework based on the Bidirectional Encoder Representations from Transformers (BERT). In this hybrid method, BERT is used to train word vector representation. Convolutional neural network (CNN) capture static features. As a supplement, a bi-gated recurrent neural network (BiGRU) is adopted to capture contextual features. Furthermore, an attention mechanism is introduced to assign the weight of salient words. The experimental results confirmed that the proposed model significantly outperforms the other state-of-the-art baseline methods.

In the rapidly evolving Internet of Things (IoT) landscape, accurate indoor positioning is increasingly vital. The proposed algorithm synergizes an ultrawideband (UWB) sensor with an inertial measurement unit (IMU) and artificial intelligence to obtain precise positioning in nonline-of-sight (NLOS) scenarios. In the proposed UWB module, a large language model (LLM) such as bidirectional encoder representations from transformers (BERT) algorithm is designed to utilize the channel impulse response (CIR) for effective NLOS identification and UWB ranging trustworthiness evaluation. Concurrently, the IMU module is also designed with BERT to recognize various pedestrian activity states, thereby optimizing positioning. BERT’s self-attention mechanism and deep learning (DL) bidirectional training efficiently extract essential features from sequential data, capturing both local and global information. The integration of both UWB and IMU through a proposed tightly coupled algorithm significantly boosts positioning performance. Experimental campaigns demonstrate an average NLOS identification accuracy, line-of-sight (LOS), and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${F}2$ </tex-math></inline-formula> of 98.8%, 99.4%, and 0.9926, respectively. These performances surpass the state-of-the-art least-squares support vector machine (LS-SVM), convolutional neural network (CNN), and CNN with long short-term memory (CNN-LSTM) up to 17.66% in NLOS identification. In terms of pedestrian activity recognition using BERT, the BERT algorithm achieves a precision (recall) of 99.3% (99.4%), notably outperforming the CNN and CNN-LSTM by 17.9% (16.2%) and 11.9% (10.9%), respectively. Finally, the UWB-IMU algorithm significantly enhances positioning accuracy by 80.5%, outperforming Kalman, LSTM-EKF, and particle filter (PF) methods by 68.1%, 48.3%, and 45.0%, respectively. The proposed approach presents a robust solution for indoor positioning for IoT applications, particularly in challenging NLOS environments.

As the online shopping industry continues to grow at a staggering rate, e-commerce channels have also begun the use of automated systems for sentiment analysis so as to be able to assess comprehension of user reviews. Over the past few years, machine learning (ML) has come of age with the introduction of deep learning models such as Convolutional Neural Networks (CNNs) and Bidirectional Encoder Representations from Transformers (BERT) which have greatly improved the levels of accuracy achieved in sentiment analysis. This paper aims to address this problem by proposing a hybrid model, based on networks of convolutional neural networks (CNNs) and BERT, for the purposes of e-commerce sentiment classification. Posting more plausible situations, academic findings, and perspectives for future research, we focus more on practical issues. When we compared traditional approaches with our hybrid, it became clear that the model performs better in many dimensions: accuracy, precision, and progressively recall

Bidirectional Encoder Representations from Transformers (BERT) and BERT-based approaches are the current state-of-the-art in many natural language processing (NLP) tasks; however, their application to document classification on long clinical texts is limited. In this work, we introduce four methods to scale BERT, which by default can only handle input sequences up to approximately 400 words long, to perform document classification on clinical texts several thousand words long. We compare these methods against two much simpler architectures - a word-level convolutional neural network and a hierarchical self-attention network - and show that BERT often cannot beat these simpler baselines when classifying MIMIC-III discharge summaries and SEER cancer pathology reports. In our analysis, we show that two key components of BERT - pretraining and WordPiece tokenization - may actually be inhibiting BERT's performance on clinical text classification tasks where the input document is several thousand words long and where correctly identifying labels may depend more on identifying a few key words or phrases rather than understanding the contextual meaning of sequences of text.

Fenomena bullying di media sosial, khususnya di Twitter, telah menjadi isu yang semakin memprihatinkan dengan dampak signifikan terhadap kesehatan mental pengguna. Dalam rangka mengatasi masalah ini, deteksi otomatis tweet yang mengandung konten bullying menjadi sangat penting. Penelitian ini bertujuan untuk membandingkan performa dua model pemrosesan bahasa alami terbaru, yaitu BERT (Bidirectional Encoder Representations from Transformers) dan XLNet, dalam klasifikasi tweet yang mengandung bullying. Metodologi penelitian ini melibatkan pengumpulan dataset tweet yang telah dilabeli sebagai bullying atau non-bullying. Proses preprocessing teks dilakukan untuk membersihkan dan menyiapkan data sebelum digunakan dalam pelatihan model. Kedua model, BERT dan XLNet, dilatih dan diuji menggunakan dataset yang sama. Evaluasi performa dilakukan dengan menggunakan metrik akurasi, presisi, recall, dan F1-score. Hasil penelitian menunjukkan bahwa kedua model memiliki kemampuan yang baik dalam mengidentifikasi tweet bullying, akan tetapi XLNet menunjukkan performa yang lebih unggul dibandingkan BERT dengan tingkat akurasi sebesar 95%. Dengan nilai presisi = 100%, recall = 0,87%, dan F1-score = 0,88%. XLNet mampu menangkap konteks dan nuansa bahasa yang lebih kompleks dalam tweet, yang berkontribusi pada akurasi klasifikasi yang lebih tinggi. Penelitian ini memberikan kontribusi penting dalam bidang deteksi bullying di media sosial dengan menunjukkan bahwa penggunaan model XLNet lebih efektif dibandingkan BERT. Temuan ini dapat membantu platform seperti Twitter dalam mengidentifikasi dan mencegah konten bullying, sehingga menciptakan lingkungan online yang lebih aman bagi pengguna, serta dapat digunakan sebagai dasar untuk pengembangan sistem deteksi bullying yang lebih canggih dan efisien di masa depan. Abstract The phenomenon of bullying on social media, particularly on Twitter, has become an increasingly concerning issue with significant impacts on users' mental health. In order to address this issue, automatic detection of tweets containing bullying content is crucial. This study aims to compare the performance of two recent natural language processing models, namely BERT (Bidirectional Encoder Representations from Transformers) and XLNet, in the classification of tweets containing bullying. The research methodology involves collecting a dataset of tweets that have been labelled as bullying or non-bullying. Text preprocessing is done to clean and prepare the data before it is used in model training. Both models, BERT and XLNet, were trained and tested using the same dataset. Performance evaluation was conducted using accuracy, precision, recall, and F1-score metrics. The results show that both models have a good ability to identify bullying tweets, but XLNet shows superior performance compared to BERT with an accuracy rate of 95%. With precision = 100%, recall = 0.87%, and F1-score = 0.88%. XLNet is able to capture more complex context and language nuances in tweets, which contributes to higher classification accuracy. This research makes an important contribution to the field of bullying detection on social media by showing that the use of the XLNet model is more effective than BERT. These findings can help platforms like Twitter identify and prevent bullying content, thereby creating a safer online environment for users, and can be used as a basis for the development of more sophisticated and efficient bullying detection systems in the future.

Multitask learning (MTL) and data augmentation are becoming increasingly popular in natural language processing (NLP). These techniques are particularly useful when data are scarce. In MTL, knowledge learned from one task is applied to another. To address data scarcity, data augmentation facilitates by providing additional synthetic data during model training. In NLP, the bidirectional encoder representations from transformers (BERT) model is the default candidate for various tasks. MTL and data augmentation using BERT have yielded promising results. However, a detailed study regarding the effect of using MTL in different layers of BERT and the benefit of data augmentation in these configurations has not been conducted. In this study, we investigate the use of MTL and data augmentation from generative models, specifically for category classification, sentiment classification, and aspect-opinion sequence-labeling using BERT. The layers of BERT are categorized into top, middle, and bottom layers, which are frozen, shared, or unshared. Experiments are conducted to identify the optimal layer configuration for improved performance compared with that of single-task learning. Generative models are used to generate augmented data, and experiments are performed to reveal their effectiveness. The results indicate the effectiveness of the MTL configuration compared with single-task learning as well as the effectiveness of data augmentation using generative models for classification tasks.

Emails are the simplest way to communicate between users. But increasing rate of cybercrime activities require shrewd use of email. Phishing email is one of the most perilous threats nowadays. Through phishing email, attackers want to steal the sensitive information of the email users. This sensitive information includes username, password, credit card details etc. These may cause excessive financial loss. Many anti-phishing methods exist in literature to detect phishing emails. But criminals use new methods day by day, which causes challenge to build anti-phishing methods to prevent phishing emails. In this paper the performance of two deep learning models for detection of phishing email have been compared. The first model uses convolution neural network with Global Vector (GloVe) word embedding where Bidirectional Encoder Representations from Transformers (BERT) model with fine tuning has been used in second model. The proposed method detects the phishing email by analyzing the content of the email. Some widely used datasets (lingSpam, enronSpamSubset, completeSpamAssassin, Jose Nazario's phishing dataset and Enron email dataset) are merged together and applied to measure the performance of the model. It is found that the GloVe word embedding achieves better accuracy (98%) than BERT model (96%) in detection of phishing emails in the present context.

The traditional topic-based auditing model lacks the ability of multi-object and multi-abnormal correlation auditing, which makes it impossible to solve the multi-scenario and multi-factor correlation-based auditing problem. This paper designs an intelligent power marketing audit model based on a knowledge graph. First, an entity identification and relationship extraction method for power marketing business based on NLP (natural language processing) and sequence annotation technology is proposed, and the description content is imported into the knowledge graph database; then, semantic disambiguation and knowledge are carried out by using bidirectional encoder representation from transformers (BERT). Link to build a knowledge map of business audit rules: Finally, an experimental analysis is carried out by taking the copying and receiving business with a large business volume in the marketing audit work as an example, and it is verified that the proposed model can effectively improve the information analysis ability and the audit accuracy of the audit work.

For the traditional model based on the deep learning method most used CNN(convolutional neural networks) or RNN(Recurrent neural Network) model and is based on the dynamic character-level embedding or word-level embedding as input, so there is a problem that the text feature extraction is not comprehensive. In the development environment of the Internet of Things, A method of Automatic text classification based on BERT(Bidirectional Encoder Representations from Transformers) and Feature Fusion was proposed in this paper. Firstly, the text-to-dynamic character-level embedding is transformed by the BERT model, and the BiLSTM(Bi-directional Long-Short Term Memory) and CNN output features are combined and merged to make full use of CNN to extract the advantages of local features and to use BiLSTM to have the advantage of memory to link the extracted context features to better represent the text, so as to improve the accuracy of text classification task. A comparative study with state-of-the-art approaches manifests the proposed method outperforms the state-of-the-art methods in accuracy. It can effectively improve the accuracy of tag prediction for text data with sequence features and obvious local features.

Mood disorders are ubiquitous mental disorders with familial aggregation. Extracting family history of psychiatric disorders from large electronic hospitalization records is helpful for further study of onset characteristics among patients with a mood disorder. This study uses an observational clinical data set of in-patients of Nanjing Brain Hospital, affiliated with Nanjing Medical University, from the past 10 years. This paper proposes a pretrained language model: Bidirectional Encoder Representations from Transformers (BERT)–Convolutional Neural Network (CNN). We first project the electronic hospitalization records into a low-dimensional dense matrix via the pretrained Chinese BERT model, then feed the dense matrix into the stacked CNN layer to capture high-level features of texts; finally, we use the fully connected layer to extract family history based on high-level features. The accuracy of our BERT–CNN model was 97.12 ± 0.37% in the real-world data set from Nanjing Brain Hospital. We further studied the correlation between mood disorders and family history of psychiatric disorder.