- Log In/Sign Up
- P-ISSN1738-6764
- E-ISSN2093-7504
- KCI
ISSN : 1738-6764
Vol.17 No.4
Abstract
Named entity recognition (NER) is a crucial task for NLP, which aims to extract information from texts. To build NER systems, deep learning (DL) models are learned with dictionary features by mapping each word in the dataset to dictionary features and generating a unique index. However, this technique might generate noisy labels, which pose significant challenges for the NER task. In this paper, we proposed DLdictionary features, and evaluated them on two datasets, including the OntoNotes 5.0 dataset and our new infectious disease outbreak dataset named GFID. We used (1) a Bidirectional Long Short-Term Memory (BiLSTM) character and (2) pre-trained embedding to concatenate with (3) our proposed features, named the Convolutional Neural Network (CNN), BiLSTM, and self-attention dictionaries, respectively. The combined features (1-3) were fed through BiLSTM - Conditional Random Field (CRF) to predict named entity classes as outputs. We compared these outputs with other predictions of the BiLSTM character, pre-trained embedding, and dictionary features from previous research, which used the exact matching and partial matching dictionary technique. The findings showed that the model employing our dictionary features outperformed other models that used existing dictionary features. We also computed
Abstract
The purpose of this study was to explore how designers use software-based design tools for ideation and collaboration (for two cases: with designers and with developers). We conducted logistic regression analysis and random forest analysis. Software-based design tools are more popular among product designers and affiliated with design organizations with 51 to 100 members. We identify the features that influence designers to use design tools for the ideation and collaboration, and how these usage patterns are interrelated. Interrelated usage pattern is a key consideration for location of the menu and convenience of use. The results imply that reinforcement of the design tool features per designer profile is required and that design management should be consistent with the field of design and the nature of the organization.
Abstract
In this study, we analyzed the factors that affect public awareness campaigns on social media platforms and developed an integrated model for measuring the persuasiveness of environmental social media campaigns. A survey questionnaire was created and distributed on Facebook with the goal of reaching individuals in their 20s and 40s in Vietnam, and 395 valid replies were gathered. The findings showed that the STOPS was reconfirmed as a suitable theoretical framework for analyzing the public's behaviour intention to conduct information related to the issue of fine dust, especially on social media. Furthermore, it also showed that social media efficacy has a moderating effect on the relationship between public’s situational recognition and informational behaviour intention. This suggested that through social media platforms, personal characteristics play a vital part in developing effective environmental campaigns. Implications for both theory and practice were discussed.
Abstract
This pilot study examined the contribution of citizen science approach to the datification of factors influencing the progress of cognitive health of the older adults. Newspapers were reviewed and FGIs of field workers at a Day Care Center gathered relevant data from citizen. Two questions were put forward; whether new factors are drawn from citizen knowledge; if yes, whether they represent a new type of data. ‘Aesal’, personality of the older adults with dementia is noted as a new dementia affecting factor. The data on personality also present a new challenge for scientific measurement. The relationship between personality or psychology of the older adults and the risk of getting dementia has been a research field for a long time, yet the impact of personality on the progress of dementia has not been examined scientifically. Because of communication difficulties with the older adults with dementia, new types of indicators and new ways of measurements thus need to be developed.
Abstract
The 2020 US Presidential Election was a highly-anticipated moment for our global society. During the election period, the most intriguing issue was who would be the winner—Trump or Biden? Among the possible main themes of the 2020 election, from the COVID-19 pandemic to racism, this study focused on feminism (‘women’) as a main component of Biden’s victory. To explore the character of Biden’s supporters, this paper focused on internet spaces as a source of public opinion. To guide the data analysis, this study employed four indices from empirical studies on Big Data analytics: issue salience, attention diversity, emotional mentioning, and semantic cohesion. The main finding of this study was that the representative keyword ‘women’ appeared more prevalently within content related to Biden than Trump, and the keyword pairs indicated that female voters were the main reason for Trump’s failure but the root cause of Biden’s victory. The results of this study indicated the role of the internet as a forum for public opinion and a fountain of political knowledge, which requires more rigorous investigation by researchers.
Abstract
This ethnographic multiple case study, based on Zappa-Hollman and Duff’s construct of individual networks of practice (INoPs), explored English as a second language (L2) competence development and socialization process of a group of English-major undergraduates through their social connections and interactions at a public university located in an underdeveloped city in Northwest China. The study lasted for one academic semester and three students were selected as primary participants. Semi-structured interviews, student observations in English-related micro-settings, and associated texts were used to collect data. These data were coded to identify the thematic categories, and then data triangulation and member checking were conducted to select the most representative evidence to provide an in-depth description of students’ perspective about mediating their English L2 socialization by their INoPs. Findings showed that factors in the formation of students’ INoPs, including intensity, density, and nature, played significant roles in their academic or affective returns from their English learning, both of which had a substantial influence on the students’ English L2 socialization. Considering that the macro-setting was a non-English, underdeveloped monolingual society, both educational institutions and individual students need to seek and create more English-mediated interactional opportunities to develop their English proficiency and adapt to local English learning communities.
Abstract
With the deepening of population aging, pension has become an urgent problem in most countries. Community smart pension can effectively resolve the problem of traditional pension, as well as meet the personalized and multi-level needs of the elderly. To predict the pension intention of the elderly in the community more accurately, this paper uses the decision tree classification method to classify the pension data. After missing value processing, normalization, discretization and data specification, the discretized sample data set is obtained. Then, by comparing the information gain and information gain rate of sample data features, the feature ranking is determined, and the C4.5 decision tree model is established. The model performs well in accuracy, precision, recall, AUC and other indicators under the condition of 10-fold crossvalidation, and the precision was 89.5%, which can provide the certain basis for government decision-making.
Abstract
The purpose of this study was to identify factors affecting Visual Display Terminal (VDT) syndrome for elementary school students in the digital learning environment. Multiple regression analyses were performed to identify the factors affecting VDT syndrome in the digital learning environment. This was conducted with 256 elementary school students in grades 5-6 with more than a year of experience in digital learning. The regression model explained 41% of elementary school students' VDT syndrome in the digital learning environment. Variables significantly affecting VDT syndrome include game addiction, sleep time, and air quality with game addiction as the most influential. In the digital learning environment, VDT syndrome is significant because it has physical and psychological impacts on the growth of elementary school students. Therefore, it is necessary to develop guidelines for ideal computer usage habits for this age group.
Abstract
The prevalence of We-Media short videos has attracted emerging independent fashion designers (EIFD), a new force in the fashion industry directing their brand promotion to We-Media for amassing online followers. However, compared to famous content generators, EIFDs' creative, design-based visual appeal has not provided them with the significant edge. The former’s success is admittedly supported by the platform backstage algorithm. Yet, the content is the cornerstone for building relationship between the sender and the reception. The authentic perception of the content is one of the basic appeals for which the audience chooses to follow the source. Therefore, with the EIFD short video as the research content, this study is established from the audience's perspective to understand the different dimensions of their authentic perceptions of EIFDs short video. The study was conducted mainly in the form of the Q method. The collection of 52 Q samples were realized through the Focus Group Interview and literature review on multidimensional authenticity. Thirty-six subjects participated in the sorting of the Q-sets. Finally, four dimensions of audience authenticity perceptions of EIFDs were derived: ‘ingenuity’, ‘relevant’, ‘transparent’, and ‘experiential’. The corresponding short video content design strategies are suggested for effective communication of EIFDs and their personal brands.