Search

In the food domain, text mining techniques are extensively employed to derive valuable insights from large volumes of text data, facilitating applications such as aiding food recalls, offering personalized recipes, and reinforcing food safety regulation. To provide researchers and practitioners with a comprehensive understanding of the latest technology and application scenarios of text mining in the food domain, the pertinent literature is reviewed and analyzed. Initially, the fundamental concepts, principles, and primary tasks of text mining, encompassing text categorization, sentiment analysis, and entity recognition, are elucidated. Subsequently, an analysis of diverse types of data sources within the food domain and the characteristics of text data mining is conducted, spanning social media, reviews, recipe websites, and food safety reports. Furthermore, the applications of text mining in the food domain are scrutinized from the perspective of various scenarios, including leveraging consumer food reviews and feedback to enhance product quality, providing personalized recipe recommendations based on user preferences and dietary requirements, and employing text mining for food safety and fraud monitoring. Lastly, the opportunities and challenges associated with the adoption of text mining techniques in the food domain are summarized and evaluated. In conclusion, text mining holds considerable potential for application in the food domain, thereby propelling the advancement of the food industry and upholding food safety standards. [ABSTRACT FROM AUTHOR]

Affective understanding of language is an important research focus in artificial intelligence. The large-scale annotated datasets of Chinese textual affective structure (CTAS) are the foundation for subsequent higher-level analysis of documents. However, there are very few published datasets for CTAS. This paper introduces a new benchmark dataset for the task of CTAS to promote development in this research direction. Specifically, our benchmark is a CTAS dataset with the following advantages: (a) it is Weibo-based, which is the most popular Chinese social media platform used by the public to express their opinions; (b) it includes the most comprehensive affective structure labels at present; and (c) we propose a maximum entropy Markov model that incorporates neural network features and experimentally demonstrate that it outperforms the two baseline models. [ABSTRACT FROM AUTHOR]

Compared to ordinary news, fake news is characterized by faster dissemination and lower production cost and therefore causes a great social harm. For these reasons, the challenge to efficiently and accurately detect fake news has attracted a lot of attention in the research community. We propose a T wo- R ound I nconsistency-based M ulti-m o dal fusi o n N etwork (TRIMOON) for fake news detection, which consists of three main components: the multi-modal feature extraction module, the multi-modal feature fusion module and the classification module. To filter the noise generated in the fusion process, we perform a two-fold inconsistency detection, once before and once after the fusion process. Experimental results also prove this to be quite effective. Our proposed TRIMOON is evaluated on both the Chinese and the English datasets, and our model outperforms the state-of-the-art approaches on several classification evaluation metrics. • A two-round inconsistency-based multi-modal fusion network for fake news detection. • Effectively suppresses fusion noise when images and text are inconsistent. • A multi-modal fusion mechanism for strengthening the leading role of text modality. • Experimental results show that our method obtains the state-of-the-art performance. [ABSTRACT FROM AUTHOR]

Personal medication intake detection aims to automatically detect tweets that show clear evidence of personal medication consumption. It is a research topic that has attracted considerable attention to drug safety surveillance. This task is inevitably dependent on medical domain information, and the current main model for this task does not explicitly consider domain information. To tackle this problem, we propose a domain attention mechanism for recurrent neural networks, LSTMs, with a multi-level feature representation of Twitter data. Specifically, we utilize character-level CNN to capture morphological features at the word level. Subsequently, we feed them with word embeddings into a BiLSTM to get the hidden representation of a tweet. An attention mechanism is introduced over the hidden state of the BiLSTM to attend to special medical information. Finally, a classification is performed on the weighted hidden representation of tweets. Experiments over a publicly available benchmark dataset show that our model can exploit a domain attention mechanism to consider medical information to improve performance. For example, our approach achieves a precision score of 0.708, a recall score of 0.694, and a F1 score of 0.697, which is significantly outperforming multiple strong and relevant baselines. [ABSTRACT FROM AUTHOR]

In the pinyin-based Chinese input method engine (IME), its performance depends mainly on the Pinyin-to-Chinese (P2C) conversion module. Traditional methods for P2C follow a pipeline procedure, which typically suffers from error propagation. Also, the ability to input the whole sentence of pinyin-based Chinese IME for domain-specific application needs to be improved. In this paper, we propose a neural self-attention model for Pinyin Sequence to Chinese Sequence (PS2CS) conversion method, which directly infers the entire Chinese sequence by feeding the unsegmented pinyin character sequence into. Our experimental results show that the proposed method outperforms baselines and the commercial IME on specific medical domain dataset, and also achieves comparable performance on the domain-general dataset. [ABSTRACT FROM AUTHOR]

Background: Named entity recognition (NER) on Chinese electronic medical/healthcare records has attracted significantly attentions as it can be applied to building applications to understand these records. Most previous methods have been purely data-driven, requiring high-quality and large-scale labeled medical data. However, labeled data is expensive to obtain, and these data-driven methods are difficult to handle rare and unseen entities.Methods: To tackle these problems, this study presents a novel multi-task deep neural network model for Chinese NER in the medical domain. We incorporate dictionary features into neural networks, and a general secondary named entity segmentation is used as auxiliary task to improve the performance of the primary task of named entity recognition.Results: In order to evaluate the proposed method, we compare it with other currently popular methods, on three benchmark datasets. Two of the datasets are publicly available, and the other one is constructed by us. Experimental results show that the proposed model achieves 91.07% average f-measure on the two public datasets and 87.05% f-measure on private dataset.Conclusions: The comparison results of different models demonstrated the effectiveness of our model. The proposed model outperformed traditional statistical models. [ABSTRACT FROM AUTHOR]

• A class of concept feature for aspect terms grouping task is proposed. • It uses location-base attentional context for the task for the first time. • A gate-based feature fusion neural network is developed. • An experimental studies on four datasets demonstrate the effectiveness of the model. We introduce a neural method that is able to fuse concepts from a knowledge base with the context information for the task of grouping of aspect terms. Rather than only using context information, we use the corresponding concepts of aspect terms as additional information for aspect terms representation. We also introduce a location-based attention mechanism for accurately representing context features. As both the concept and the aspect term are same level features, i.e. aspect level features, we develop a model with gating mechanism to fuse them together. All of the above features are fed into a parallel metric learning network which has the ability to learn an easier grouping representation of samples. Experimental results demonstrate that our approach outperforms different baselines and model variants on five datasets. [ABSTRACT FROM AUTHOR]

Topic and sentiment joint modelling has been successfully used in sentiment analysis for product reviews. However, the problem of text sparse is universal with the widespread smart devices and the shorter product reviews. In this paper, we propose a joint sentiment-topic model WSTM (Word-pair Sentiment-Topic Model) for the short text reviews, detecting sentiments and topics simultaneously from the text, especially considering the text sparse problem. Unlike other topic models modelling the generative process of each document, our directly models the generation of the word-pair set from the whole global corpus. In the generative process of WSTM, all of the words in a sentence have the same sentiment polarity, and two words in a word-pair have the same topic. We apply WSTM to two real-life Chinese product review datasets to verify its performance. In three experiments, compared with the existing approaches, the results demonstrate WSTM is quantitatively effective on both topic discovery and document level sentiment. [ABSTRACT FROM AUTHOR]

Existing studies learn sentiment-specific word representations to boost the performance of Twitter sentiment classification, via encoding both n-gram and distant supervised tweet sentiment information in learning process. Pioneer efforts explicitly or implicitly assume that all words within a tweet have the same sentiment polarity as that of the whole tweet, which basically ignores the word its own sentiment polarity. To alleviate this problem, we propose to learn sentiment-specific word embedding by exploiting both the lexicon resource and distant supervised information. In particular, we develop a multi-level sentiment-enriched word embedding learning method, which employs a parallel asymmetric neural network to model n-gram, word-level sentiment, and tweet-level sentiment in the learning process. Extensive experiments on standard benchmarks demonstrate our approach outperforms state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Brain penumbra is a critical condition that is closely related to stroke. Thus, there is high demand for fast and accurate segmentation of penumbra tissue in magnetic resonance images. However, most convolutional neural networks (CNNs) focus on learning contextual semantic information from two-dimensional imaging slides, ignoring the spatiotemporal correlations among adjacent slides. Here, we propose an encoder-decoder network (ConvLSTM-Net) with a specifically convolutional long short-term memory skip connection to extract the spatiotemporal correlations of features of adjacent slices in a non-linear manner. A mixed loss function is also used to improve the segmentation performance. We test the proposed method on the penumbra segmentation challenge and obtain an average Dice score over 80%, indicating that its performance is superior to or comparable with that of state-of-the-art segmentation methods. A mixed loss function provides positive support for the stability of model training. In addition, we visualize two representative samples to improve the interpretability of the results of ConvLSTM-Net. [ABSTRACT FROM AUTHOR]

Background: Blood cultures are often performed to detect patients who has a serious illness without infections and patients with bloodstream infections. Early positive blood culture prediction is important, as bloodstream infections may cause inflammation of the body, even organ failure or death. However, existing work mainly adopts statistical models with laboratory indicators, and fails to make full use of textual description information from EHRs.Methods: We study the problem of positive blood culture prediction by using neural network model. Specifically, we first construct dataset from raw EHRs. Then we propose a hybrid neural network which incorporates attention based Bi-directional Long Short-Term Memory and Autoencoder networks to fully capture the information in EHRs.Results: In order to evaluate the proposed method, we constructe a dataset which consists of totally 5963 patients who had one or more blood cultures tests during hospitalization. Experimental results show that the proposed neural model gets 91.23% F-measure for this task.Conclusions: The comparison results of different models demonstrated the effectiveness of our model. The proposed model outperformed traditional statistical models. [ABSTRACT FROM AUTHOR]

• An enhanced multi-modal graph convolutional network is proposed for classifying neuropsychiatric disorders. • The enhanced GCN based on sGraphs and fGraphs. • The features filtered from the sGraph are used to enhance the weights of the corresponding edges in the fGraph, and a multi-layer GCN is used for training and prediction. It has been proven that neuropsychiatric disorders (NDs) can be associated with both structures and functions of brain regions. Thus, data about structures and functions could be usefully combined in a comprehensive analysis. While brain structural MRI (sMRI) images contain anatomic and morphological information about NDs, functional MRI (fMRI) images carry complementary information. However, efficient extraction and fusion of sMRI and fMRI data remains challenging. In this study, we develop an enhanced multi-modal graph convolutional network (MME-GCN) in a binary classification between patients with NDs and healthy controls, based on the fusion of the structural and functional graphs of the brain region. First, based on the same brain atlas, we construct structural and functional graphs from sMRI and fMRI data, respectively. Second, we use machine learning to extract important features from the structural graph network. Third, we use these extracted features to adjust the corresponding edge weights in the functional graph network. Finally, we train a multi-layer GCN and use it in binary classification task. MME-GCN achieved 93.71% classification accuracy on the open data set provided by the Consortium for Neuropsychiatric Phenomics. In addition, we analyzed the important features selected from the structural graph and verified them in the functional graph. Using MME-GCN, we found several specific brain connections important to NDs. [ABSTRACT FROM AUTHOR]