A5100432091- Sentiment Analysis and Opinion Mining
- Topic Modeling
- Health disparities and outcomes
- Asian Culture and Media Studies
- Social Media and Politics
- Access Control and Trust
- Digital Marketing and Social Media
- Human Mobility and Location-Based Analysis
- Family Support in Illness
- Japanese History and Culture
- Anomaly Detection Techniques and Applications
- Cloud Data Security Solutions
- Security and Verification in Computing
- Internet Traffic Analysis and Secure E-voting
- Misinformation and Its Impacts
- Diverse Topics in Contemporary Research
- Martial Arts: Techniques, Psychology, and Education
- Regional Development and Environment
- Child Development and Digital Technology
- Advanced Computing and Algorithms
- Intergenerational Family Dynamics and Caregiving
- Recommender Systems and Techniques
- Cultural Industries and Urban Development
- Natural Language Processing Techniques
- Media, Religion, Digital Communication
China Electric Power Research Institute
2024
Nanjing University of Information Science and Technology
2024
Shenzhen Technology University
2024
Southwest Minzu University
2024
Sejong University
2023
University of Oslo
2023
Beijing Normal University - Hong Kong Baptist University United International College
2023
Beijing Normal University
2023
Hong Kong Baptist University
2023
Galveston College
2022
User generated content on Twitter (produced at an enormous rate of 340 million tweets per day) provides a rich source for gleaning people's emotions, which is necessary deeper understanding behaviors and actions. Extant studies emotion identification lack comprehensive coverage "emotional situations" because they use relatively small training datasets. To overcome this bottleneck, we have automatically created large emotion-labeled dataset (of about 2.5 tweets) by harnessing emotion-related...
Cursing is not uncommon during conversations in the physical world: 0.5% to 0.7% of all words we speak are curse words, given that 1% first-person plural pronouns (e.g., we, us, our). On social media, people can instantly chat with friends without face-to-face interaction, usually a more public fashion and broadly disseminated through highly connected network. Will these distinctive features media lead change people's cursing behavior? In this paper, examine characteristics activity on...
The problem of automatic extraction sentiment expressions from informal text, as in microblogs such tweets is a recent area investigation. Compared to formal product reviews or news articles, one the key challenges lies wide diversity and nature that cannot be trivially enumerated captured using predefined lexical patterns. In this work, we present an optimization-based approach automatically extract for given target (e.g., movie, person) corpus unlabeled tweets. Specifically, make three...
Background: To harness the full potential of social media for epidemiological surveillance drug abuse trends, field needs a greater level automation in processing and analyzing content. Objectives: The objective study is to describe development supervised machine-learning techniques eDrugTrends platform automatically classify tweets by type/source communication (personal, official/media, retail) sentiment (positive, negative, neutral) expressed cannabis- synthetic cannabinoid–related tweets....
Breast cancer incidence and the number of breast survivors have been rapidly increasing among Chinese Korean women in United States. However, few data are available regarding quality life Asian American survivors. This qualitative study aims to describe women's perceptions their experiences. In-depth interviews with four five three oncologists were conducted Chinese, Korean, or English. Interviews recorded transcripts translated into Qualitative analyses performed by two independent coders...
A digital divide continues to be reported across and within nations, first as an access issue second of effective usage. To address the latter issue, we argue that equity should not conceptualized solely a technical or resource related issue. We developed conceptual framework based on cultural capital parental mediation investigate complexity inequity. Our in-depth case study 22 Hong Kong students revealed although information communication technology (ICT) is thoroughly integrated with...
Happiness is the eternal pursuit of mankind and also ultimate goal social governance national development. Based on data from Chinese General Social Survey, this study used a structural equation model to analyze influence class identity public service satisfaction happiness residents. The effect trust between residents’ was tested using Monte Carlo method. empirical results show that identity, trust, all had significant positive impact happiness. coefficients residents degree for those born...
This paper presents our solution for the i2b2 sentiment classification challenge. Our hybrid system consists of machine learning and rule-based classifiers. For classifier, we investigate a variety lexical, syntactic knowledge-based features, show how much these features contribute to performance classifier through experiments. propose an algorithm automatically extract effective lexical patterns from training examples. The experimental results that outperforms baseline using unigram...
Background Depression is a major health concern for college students due to its substantial morbidity and mortality. Although low parental education has been identified as factor in depression students, the mechanisms through which educational achievement affects students' are not well understood. We tested whether adverse family environments mediate relationship between level among Chinese students. Methods A total of 5180 respondents were selected using cross-sectional survey. examined...
Novel coronavirus, now named COVID-19, has swept the world, which is regarded as 'public enemy number one' by WHO. In these months, coronavirus become a hot topic and led various public opinion. The traditional strategies for opinion analyzing seldom take entities behaviors into consideration. Focusing on high fluctuation of novel event, we propose Key-Information-oriented Convolutional Neural Network (KINCNN) to analyze both relevant in addition trend Chinese corpus. Firstly, establish...
The relationship between educational attainment and ischaemic heart disease (IHD) is limited in evidence middle-income countries like China. Exploring lifestyle-related mediators, which might be not universal socioeconomic status health outcomes diverse regions, can contribute to interventions targeted at the Chinese narrow gap IHD.
The modern academic world can hardly boast of substantial research on how people become loyal to businesses thanks TikTok. current seeks add some knowledge the field by exploring impact that TikTok services' quality and satisfaction from using it have Russian Chinese users' loyalty opinion leaders in this social network. analysis data collected survey 400 users was done means partial least squares structural equation modeling method. This allowed obtaining results confirmed e-service...
The information measurement of the NAR (network access requester) is key element for trusted network access. only issues TNC (trusted connection) proposed conception integrity and pointed out that if measurements passed can NAS ((network server) let endpoint enter. But no concrete techniques are expatiated in TNC, related specification IMM (integrity model) too complex to implement. Virtually, cannot be localized integrity. In this paper, a new architecture proposed, which not platform, but...