Search results

In the era of Big Data, network digital resources are growing rapidly, especially the short-text resources, such as tweets, comments, messages and so on, are showing a vigorous vitality. This study aims to compare the categories discriminative capacity (CDC) of Chinese language fragments with different granularities and to explore and verify feasibility, rationality and effectiveness of the low-granularity feature, such as Chinese characters in Chinese short-text classification (CSTC).

This study takes discipline classification of journal articles from CSSCI as a simulation environment. On the basis of sorting out the distribution rules of classification features with various granularities, including keywords, terms and characters, the classification effects accessed by the SVM algorithm are comprehensively compared and evaluated from three angles of using the same experiment samples, testing before and after feature optimization, and introducing external data.

The granularity of a classification feature has an important impact on CSTC. In general, the larger the granularity is, the better the classification result is, and vice versa. However, a low-granularity feature is also feasible, and its CDC could be improved by reasonable weight setting, even exceeding a high-granularity feature if synthetically considering classification precision, computational complexity and text coverage.

This is the first study to propose that Chinese characters are more suitable as descriptive features in CSTC than terms and keywords and to demonstrate that CDC of Chinese character features could be strengthened by mixing frequency and position as weight.

More and more e-commerce web sites are using online customer reviews (OCRs) for customer segmentation. However, for durable products, customer purchases, and reviews only once for a long time, as while the product review score may highly affected by service factors or be “gently” evaluated. Existing regression or machine learning-based methods suffer from low accuracy when applied to the OCRs of durable products on e-commerce web sites. The purpose of this paper is to propose a new approach for customer segment analysis base on OCRs of durable products.

The research proposes a two-stage approach that employs latent class analysis (LCA): the feature-mention matrix construction stage and the LCA-based customer segmentation stage. The approach considers reviewers’ mention on product features, and the probability-based LCA method is adopted upon the characteristics of online reviews, to effectively cluster reviewers into specified segmentations.

The research finding is that, using feature-mention instead of feature-opinion records makes segment analysis more effective. The research also finds that, LCA method can better explain the characteristics of the OCR data of durable products for customer segmentation.

The research proposes a new approach to durable product review mining for customer segmentation analysis. The segment analysis result can provide supports for new product design and development, repositioning of existing products, marketing strategy development and product differentiation.

A new approach for customer segmentation analysis base on OCRs of durable products is proposed.

The authors examine the contemporaneous and causal association between tweet features (bullishness, message volume and investor agreement) and market features (stock returns, trading volume and volatility) using 140 South African companies and a dataset of firm-level Twitter messages extracted from Bloomberg for the period 1 January 2015 to 31 March 2020.

Panel regressions with ticker fixed-effects are used to examine the contemporaneous link between tweet features and market features. To examine the link between the magnitude of tweet features and stock market features, the study uses quantile regression.

No monotonic relationship is found between the magnitude of tweet features and the magnitude of market features. The authors find no evidence that past values of tweet features can predict forthcoming stock returns using daily data while weekly and monthly data shows that past values of tweet features contain useful information that can predict the future values of stock returns.

The study is among the earlier to examine the association between textual sentiment from social media and market features in a South African context. The exploration of the relationship across the distribution of the stock market features gives new insights away from the traditional approaches which investigate the relationship at the mean.

In recent years, Chinese sentiment analysis has made great progress, but the characteristics of the language itself and downstream task requirements were not explored thoroughly. It is not practical to directly migrate achievements obtained in English sentiment analysis to the analysis of Chinese because of the huge difference between the two languages.

In view of the particularity of Chinese text and the requirement of sentiment analysis, a Chinese sentiment analysis model integrating multi-granularity semantic features is proposed in this paper. This model introduces the radical and part-of-speech features based on the character and word features, with the application of bidirectional long short-term memory, attention mechanism and recurrent convolutional neural network.

The comparative experiments showed that the F1 values of this model reaches 88.28 and 84.80 per cent on the man-made dataset and the NLPECC dataset, respectively. Meanwhile, an ablation experiment was conducted to verify the effectiveness of attention mechanism, part of speech, radical, character and word factors in Chinese sentiment analysis. The performance of the proposed model exceeds that of existing models to some extent.

The academic contribution of this paper is as follows: first, in view of the particularity of Chinese texts and the requirement of sentiment analysis, this paper focuses on solving the deficiency problem of Chinese sentiment analysis under the big data context. Second, this paper borrows ideas from multiple interdisciplinary frontier theories and methods, such as information science, linguistics and artificial intelligence, which makes it innovative and comprehensive. Finally, this paper deeply integrates multi-granularity semantic features such as character, word, radical and part of speech, which further complements the theoretical framework and method system of Chinese sentiment analysis.

Student engagement is a key factor that connects with student achievement and retention. This paper aims to identify individuals' engagement automatically in the classroom with multimodal data for supporting educational research.

The video and electroencephalogram data of 36 undergraduates were collected to represent observable and internal information. Since different modal data have different granularity, this study proposed the Fast–Slow Neural Network (FSNN) to detect engagement through both observable and internal information, with an asynchrony structure to preserve the sequence information of data with different granularity.

Experimental results show that the proposed algorithm can recognize engagement better than the traditional data fusion methods. The results are also analyzed to figure out the reasons for the better performance of the proposed FSNN.

This study combined multimodal data from observable and internal aspects to improve the accuracy of engagement detection in the classroom. The proposed FSNN used the asynchronous process to deal with the problem of remaining sequential information when facing multimodal data with different granularity.

The purpose of this paper is to provide a generalized framework that illustrates the potential for the resources, events and agents (REA) model to integrate business strategy and information systems planning. The essential point of connection, the business process, enables the REA to form a complementary platform to integrate strategic change information to support change strategies.

The paper uses a case study to illustrate application of the framework.

The framework illustrates how the expanding ontology and semantic granularity and scalability features of the REA enterprise domain ontology, support mapping a range of change strategies structured using Venkataraman's change framework.

This paper is exploratory in nature. The method uses existing case information, but the nature of the work does not lend itself to the traditional descriptive approach.

Integration of business strategy and information systems planning is critical for organizational success. Poor integration between change initiatives and systems poses a challenge in implementing change strategies. Conceptual models that support change initiatives provide users an effective medium to use domain knowledge to support change strategies.

The paper integrates existing concepts in the REA model (with some modification to the process view of the REA to adapt to multiple change initiatives). To the authors’ knowledge, there are no other papers that have offered a generalized framework for conceptualizing change initiatives of different levels.

The purpose of the study is to address the problems of low accuracy and missed detection of occluded pedestrians and small target pedestrians when using the YOLOX general object detection algorithm for pedestrian detection. This study proposes a multi-level fine-grained YOLOX pedestrian detection algorithm.

First, to address the problem of the original YOLOX algorithm in obtaining a single perceptual field for the feature map before feature fusion, this study improves the PAFPN structure by adding the ResCoT module to increase the diversity of the perceptual field of the feature map and divides the pedestrian multi-scale features into finer granularity. Second, for the CSPLayer of the PAFPN, a weight gain-based normalization-based attention module (NAM) is proposed to make the model pay more attention to the context information when extracting pedestrian features and highlight the salient features of pedestrians. Finally, the authors experimentally determined the optimal values for the confidence loss function.

The experimental results show that, compared with the original YOLOX algorithm, the AP of the improved algorithm increased by 2.90%, the Recall increased by 3.57%, and F1 increased by 2% on the pedestrian dataset.

The multi-level fine-grained YOLOX pedestrian detection algorithm can effectively improve the detection of occluded pedestrians and small target pedestrians.

The authors introduce a multi-level fine-grained ResCoT module and a weight gain-based NAM attention module.

The purpose of this study is to investigate and demonstrate the advancements achieved in the field of chest X-ray image captioning through the utilization of dynamic convolutional encoder–decoder networks (DyCNN). Typical convolutional neural networks (CNNs) are unable to capture both local and global contextual information effectively and apply a uniform operation to all pixels in an image. To address this, we propose an innovative approach that integrates a dynamic convolution operation at the encoder stage, improving image encoding quality and disease detection. In addition, a decoder based on the gated recurrent unit (GRU) is used for language modeling, and an attention network is incorporated to enhance consistency. This novel combination allows for improved feature extraction, mimicking the expertise of radiologists by selectively focusing on important areas and producing coherent captions with valuable clinical information.

In this study, we have presented a new report generation approach that utilizes dynamic convolution applied Resnet-101 (DyCNN) as an encoder (Verelst and Tuytelaars, 2019) and GRU as a decoder (Dey and Salemt, 2017; Pan et al., 2020), along with an attention network (see Figure 1). This integration innovatively extends the capabilities of image encoding and sequential caption generation, representing a shift from conventional CNN architectures. With its ability to dynamically adapt receptive fields, the DyCNN excels at capturing features of varying scales within the CXR images. This dynamic adaptability significantly enhances the granularity of feature extraction, enabling precise representation of localized abnormalities and structural intricacies. By incorporating this flexibility into the encoding process, our model can distil meaningful and contextually rich features from the radiographic data. While the attention mechanism enables the model to selectively focus on different regions of the image during caption generation. The attention mechanism enhances the report generation process by allowing the model to assign different importance weights to different regions of the image, mimicking human perception. In parallel, the GRU-based decoder adds a critical dimension to the process by ensuring a smooth, sequential generation of captions.

The findings of this study highlight the significant advancements achieved in chest X-ray image captioning through the utilization of dynamic convolutional encoder–decoder networks (DyCNN). Experiments conducted using the IU-Chest X-ray datasets showed that the proposed model outperformed other state-of-the-art approaches. The model achieved notable scores, including a BLEU_1 score of 0.591, a BLEU_2 score of 0.347, a BLEU_3 score of 0.277 and a BLEU_4 score of 0.155. These results highlight the efficiency and efficacy of the model in producing precise radiology reports, enhancing image interpretation and clinical decision-making.

This work is the first of its kind, which employs DyCNN as an encoder to extract features from CXR images. In addition, GRU as the decoder for language modeling was utilized and the attention mechanisms into the model architecture were incorporated.

This study builds on a first study by Macdonald and Birdi (2019) that argues the concept of neutrality within library and information science (LIS) demands a sensitivity to context often omitted in existing literature. This study aims to develop the conceptual architecture of LIS neutrality in a way that is more conducive to reconciling the contextual nuance found in within the first study.

The approach taken develops LIS neutrality through a Wittgensteinian lens. Two distinct ideas are explored. First, Wittgenstein's notion of a “grammatical investigation” is used to map the varied contexts in which neutrality is used within professional practice. Liberal neutrality is explored as an analogy to lend plausibility to the concept's heterogeneity. Second, Wittgenstein's “family resemblance” develops the concept in a way that facilitates greater contextual understanding.

Three features of liberal neutrality literature: conceptual heterogeneity, distinct justifications for specific conceptions and the possibility that neutrality may operate with limited scope are applied to LIS neutrality. All three features successfully translate, leaving “latent conceptual space” to understand LIS neutrality as nuanced and multifaceted. Second, “family resemblance” also translates successfully, bringing its own pedagogical benefits.

This study's originality lies in its development of LIS neutrality using a descriptive Wittgensteinian lens. Understanding the concept via this paradigm may facilitate a more productive discussion of LIS neutrality and pave the way for a new, less polarised, normative response to it.

One of the bottle‐necks of computer numerical control (CNC) machining is the CNC programming. It relies on the experience and skills of the CNC programmer for the generation of the CNC program. The intelligent process‐planning system described in this paper generates a process plan automatically for CNC programming. It utilizes artificial intelligent technologies such as knowledge base, blackboard system and machine learning to extract machineable features, and proposes and selects optimal tools for the machining of the given part. Its flexibility and simplicity provide a convenient way to include new techniques and knowledge. The incorporation of this system with other CAD/CAM tools could effectively automate the CNC programming process.