Search results

The paper aims to construct a spatiotemporal situational awareness framework to sense the evolutionary situation of public opinion in social media, thus assisting relevant departments in formulating public opinion control measures for specific time and space contexts.

The spatiotemporal situational awareness framework comprises situational element extraction, situational understanding and situational projection. In situational element extraction, the data on the COVID-19 vaccine, including spatiotemporal tags and text contents, is extracted. In situational understanding, the bidirectional encoder representation from transformers – latent dirichlet allocation (BERT-LDA) and bidirectional encoder representation from transformers – bidirectional long short-term memory (BERT-BiLSTM) are used to discover the topics and emotional labels hidden in opinion texts. In situational projection, the situational evolution characteristics and patterns of online public opinion are uncovered from the perspective of time and space through multiple visualisation techniques.

From the temporal perspective, the evolution of online public opinion is closely related to the developmental dynamics of offline events. In comparison, public views and attitudes are more complex and diversified during the outbreak and diffusion periods. From the spatial perspective, the netizens in hotspot areas with higher discussion volume are more rational and prefer to track the whole process of event development, while the ones in coldspot areas with less discussion volume pay more attention to the expression of personal emotions. From the perspective of intertwined spatiotemporal, there are differences in the focus of attention and emotional state of netizens in different regions and time stages, caused by the specific situations they are in.

The situational awareness framework can shed light on the dynamic evolution of online public opinion from a multidimensional perspective, including temporal, spatial and spatiotemporal perspectives. It enables decision-makers to grasp the psychology and behavioural patterns of the public in different regions and time stages and provide targeted public opinion guidance measures and offline event governance strategies.

Dunhuang murals are rich in cultural and artistic value. The purpose of this paper is to construct a novel mobile visual search (MVS) framework for Dunhuang murals, enabling users to efficiently search for similar, relevant and diversified images.

The convolutional neural network (CNN) model is fine-tuned in the data set of Dunhuang murals. Image features are extracted through the fine-tuned CNN model, and the similarities between different candidate images and the query image are calculated by the dot product. Then, the candidate images are sorted by similarity, and semantic labels are extracted from the most similar image. Ontology semantic distance (OSD) is proposed to match relevant images using semantic labels. Furthermore, the improved DivScore is introduced to diversify search results.

The results illustrate that the fine-tuned ResNet152 is the best choice to search for similar images at the visual feature level, and OSD is the effective method to search for the relevant images at the semantic level. After re-ranking based on DivScore, the diversification of search results is improved.

This study collects and builds the Dunhuang mural data set and proposes an effective MVS framework for Dunhuang murals to protect and inherit Dunhuang cultural heritage. Similar, relevant and diversified Dunhuang murals are searched to meet different demands.

The purpose of this paper is to build a mobile visual search service system for the protection of Dunhuang cultural heritage in the smart library. A novel mobile visual search model for Dunhuang murals is proposed to help users acquire rich knowledge and services conveniently.

First, local and global features of images are extracted, and the visual dictionary is generated by the k-means clustering. Second, the mobile visual search model based on the bag-of-words (BOW) and multiple semantic associations is constructed. Third, the mobile visual search service system of the smart library is designed in the cloud environment. Furthermore, Dunhuang mural images are collected to verify this model.

The findings reveal that the BOW_SIFT_HSV_MSA model has better search performance for Dunhuang mural images when the scale-invariant feature transform (SIFT) and the hue, saturation and value (HSV) are used to extract local and global features of the images. Compared with different methods, this model is the most effective way to search images with the semantic association in the topic, time and space dimensions.

Dunhuang mural image set is a part of the vast resources stored in the smart library, and the fine-grained semantic labels could be applied to meet diverse search needs.

The mobile visual search service system is constructed to provide users with Dunhuang cultural services in the smart library. A novel mobile visual search model based on BOW and multiple semantic associations is proposed. This study can also provide references for the protection and utilization of other cultural heritages.

The proliferation of bots in social networks has profoundly affected the interactions of legitimate users. Detecting and rejecting these unwelcome bots has become part of the collective Internet agenda. Unfortunately, as bot creators use more sophisticated approaches to avoid being discovered, it has become increasingly difficult to distinguish social bots from legitimate users. Therefore, this paper proposes a novel social bot detection mechanism to adapt to new and different kinds of bots.

This paper proposes a research framework to enhance the generalization of social bot detection from two dimensions: feature extraction and detection approaches. First, 36 features are extracted from four views for social bot detection. Then, this paper analyzes the feature contribution in different kinds of social bots, and the features with stronger generalization are proposed. Finally, this paper introduces outlier detection approaches to enhance the ever-changing social bot detection.

The experimental results show that the more important features can be more effectively generalized to different social bot detection tasks. Compared with the traditional binary-class classifier, the proposed outlier detection approaches can better adapt to the ever-changing social bots with a performance of 89.23 per cent measured using the F1 score.

Based on the visual interpretation of the feature contribution, the features with stronger generalization in different detection tasks are found. The outlier detection approaches are first introduced to enhance the detection of ever-changing social bots.

The outbreak of COVID-19 has become a major public health emergency worldwide. How to effectively guide public opinion and implement precise prevention and control is a hot topic in current research. Mining the spatiotemporal coupling between online public opinion and offline epidemics can provide decision support for the precise management and control of future emergencies.

This study focuses on analyzing the spatiotemporal coupling relationship between public opinion and the epidemic. First, based on Weibo information and confirmed case information, a field framework is constructed using field theory. Second, SnowNLP is used for sentiment mining and LDA is utilized for topic extraction to analyze the topic evolution and the sentiment evolution of public opinion in each coupling stage. Finally, the spatial model is used to explore the coupling relationship between public opinion and the epidemic in space.

The findings show that there is a certain coupling between online public opinion sentiment and offline epidemics, with a significant coupling relationship in the time dimension, while there is no remarkable coupling relationship in space. In addition, the core topics of public concern are different at different coupling stages.

This study deeply explores the spatiotemporal coupling relationship between online public opinion and offline epidemics, adding a new research perspective to related research. The result can help the government and relevant departments understand the dynamic development of epidemic events and achieve precise control while mastering the dynamics of online public opinion.

The deployment of vaccines is the primary task in curbing the COVID-19 pandemic. The purpose of this paper is to understand the public’s opinions on vaccines and then design effective interventions to promote vaccination coverage.

This paper proposes a research framework based on the spatiotemporal perspective to analyse the public opinion evolution towards COVID-19 vaccine in China. The framework first obtains data through crawler tools. Then, with the help of data mining technologies, such as emotion computing and topic extraction, the evolution characteristics of discussion volume, emotions and topics are explored from spatiotemporal perspectives.

In the temporal perspective, the public emotion declines in the later stage, but overall emotion performance is positive and stabilizing. This decline in emotion is mainly associated with ambiguous information about the COVID-19 vaccine. The research progress of vaccines and the schedule of vaccination have driven the evolution of public discussion topics. In the spatial perspective, the public emotion tends to be positive in 31 regions, whereas local emotion increases and decreases in different stages. The dissemination of distinctive information and the local epidemic prevention and control status may be potential drivers of topic evolution in local regions.

The analysis results of media information can assist decision-makers to accurately grasp the subjective thoughts and emotional expressions of the public in terms of spatiotemporal perspective and provide decision support for macro-control response strategies and risk communication.

Aspects extracted from the user’s historical records are widely used to define user’s fine-grained preferences for building interpretable recommendation systems. As the aspects were extracted from the historical records, the aspects that represent user’s negative preferences cannot be identified because of their absence from the records. However, these latent aspects are also as important as those aspects representing user’s positive preferences for building a recommendation system. This paper aims to identify the user’s positive preferences and negative preferences for building an interpretable recommendation.

First, high-frequency tags are selected as aspects to describe user preferences in aspect-level. Second, user positive and negative preferences are calculated according to the positive and negative preference model, and the interaction between similar aspects is adopted to address the aspect sparsity problem. Finally, an experiment is designed to evaluate the effectiveness of the model. The code and the experiment data link is: https://github.com/shiyu108/Recommendation-system

Experimental results show the proposed approach outperformed the state-of-the-art methods in widely used public data sets. These latent aspects are also as important as those aspects representing the user’s positive preferences for building a recommendation system.

This paper provides a new approach that identifies and uses not only users’ positive preferences but also negative preferences, which can capture user preference precisely. Besides, the proposed model provides good interpretability.

Twitter fake accounts refer to bot accounts created by third-party organizations to influence public opinion, commercial propaganda or impersonate others. The effective identification of bot accounts is conducive to accurately judge the disseminated information for the public. However, in actual fake account identification, it is expensive and inefficient to manually label Twitter accounts, and the labeled data are usually unbalanced in classes. To this end, the authors propose a novel framework to solve these problems.

In the proposed framework, the authors introduce the concept of semi-supervised self-training learning and apply it to the real Twitter account data set from Kaggle. Specifically, the authors first train the classifier in the initial small amount of labeled account data, then use the trained classifier to automatically label large-scale unlabeled account data. Next, iteratively select high confidence instances from unlabeled data to expand the labeled data. Finally, an expanded Twitter account training set is obtained. It is worth mentioning that the resampling technique is integrated into the self-training process, and the data class is balanced at the initial stage of the self-training iteration.

The proposed framework effectively improves labeling efficiency and reduces the influence of class imbalance. It shows excellent identification results on 6 different base classifiers, especially for the initial small-scale labeled Twitter accounts.

This paper provides novel insights in identifying Twitter fake accounts. First, the authors take the lead in introducing a self-training method to automatically label Twitter accounts from the semi-supervised background. Second, the resampling technique is integrated into the self-training process to effectively reduce the influence of class imbalance on the identification effect.

This paper aims to investigate the relationship between sentiment and review helpfulness and develop a method to fully use sentiment features in review helpfulness assessment. In addition, this paper explores whether product type influences evaluating review helpfulness.

First, a high-quality data set with a manually coded helpfulness score was constructed. Second, detailed research question methods were conducted. Finally, methods were applied to the data set to extract information gain and sentiment scores. Gradient boosting and random forest methods were used to classify the data set with these features through recall, precision and F-measure to understand the research questions.

Review sentiment has a deep relationship with review helpfulness, and it can be a strong predictor of review helpfulness by refining it into more detailed scores; a combination of sentiment scores and information gain works very well on classification for two product types. Product type does not show a significant influence on helpfulness assessment.

This paper provides a different perspective for measuring review sentiment by clarifying the relationship between sentiment and review helpfulness, analysing the role of product type in review helpfulness assessment, and proposing a high-value feature combination. In addition, the author believes that the assessment method can be effectively applied to practical works.

Social coding platforms (SCPs) have been adopted by scores of developers in building, testing and managing their codes collaboratively. Accordingly, this type of platform (site) enables collaboration between enterprises and universities (c-EU) at a lower cost in the form of online team-building projects (repositories). This paper investigates the open collaboration patterns between these two parties on GitHub by measuring their online behaviours. The purpose of this investigation is to identify the most attractive collaboration features that enterprises can offer to increase university students' participation intentions.

The research process is divided into four steps. First, the authors crawled for numerical data for each interactive repository feature created by employees of Alibaba on GitHub and identified the student accounts associated with these repositories. Second, a categorisation schema of feature classification was proposed on a behavioural basis. Third, the authors clustered the aforementioned repositories based on feature data and recognised four types of repositories (popular, formal, normal and obsolete) to represent four open collaboration patterns. The effects of the four repository types on university students' collaboration behaviour were measured using a multiple linear regression model. An ANOVA test was implemented to examine the robustness of research results. Finally, the authors proposed some practical suggestions to enhance collaboration between both sides of SCPs.

Several counterintuitive but reasonable findings were revealed, for example, those based on the “star” repository feature. The actual coding contribution of the repositories had a negative correlation with student attention. This result indicates that students were inclined to imitate rather than innovate.

This research explores the open collaboration patterns between enterprises and universities on GitHub and their impact on student coding behaviour. According to the research analysis, both parties benefit from open collaboration on SCPs, and the allocation or customisation of online repository features may affect students' participation in coding. This research brings a new perspective to the measurement of users' collaboration behaviour with output rates on SCPs.