Search results

The purpose of this paper is to develop a new method to extract medical temporal information from online health communities.

The authors trained a conditional random-filed model for the extraction of temporal expressions. The temporal relation identification is considered as a classification task and several support vector machine classifiers are built in the proposed method. For the model training, the authors extracted some high-level semantic features including co-reference relationship of medical concepts and the semantic similarity among words.

For the extraction of TIMEX, the authors find that well-formatted expressions are easy to recognize, and the main challenge is the relative TIMEX such as “three days after onset”. It also shows the same difficulty for normalization of absolute date or well-formatted duration, whereas frequency is easier to be normalized. For the identification of DocTimeRel, the result is fairly well, and the relation is difficult to identify when it involves a relative TIMEX or a hypothetical concept.

The authors proposed a new method to extract temporal information from the online clinical data and evaluated the usefulness of different level of syntactic features in this task.

Mobile fitness apps (MFAs) are increasingly popular for people to promote physical activity (PA) and further enhance health status via behavioral change techniques (BCTs), but the phenomenon of users abandoning MFAs is still common. For improving users' PA and decreasing dropout rates of MFAs, this study intends to gain insights into the effects of major BCTs-based incentive factors on users' PA under MFAs context and the gender differences in their effects.

Based on self-determination theory, three major incentive factors were chosen from the perspective of self-peer-platform incentives, i.e. self-monitoring (SM), social support (SS) and platform rewards (PR). A dataset of 4,530 users from a popular mobile fitness app was collected and was analyzed using fixed effects models.

The results show that all three types of incentive factors are positively associated with users' PA. The estimated effect sizes can be ordered as: SM > PR > SS. Moreover, social support has a stronger positive impact on PA of females than males, whereas platform rewards have a weaker positive effect on PA of females than males. In addition, the results also indicate there are no significant gender differences in the effect of self-monitoring.

There is insufficient research on systematically examining the effects of different types of incentive factors of MFAs on users' PA in one study. This study extends the current understanding of incentive factors by simultaneously examining different incentive factors and the role of gender. The findings can also provide insightful guidance for the design of MFAs.

Doctor–medical institution collaboration (DMIC) services are an emerging service mode in focal online health communities (OHCs). This new service mode is anticipated to affect user satisfaction and doctors' engagement behaviors. However, whether and how DMIC occurs is still ambiguous because the topic is rarely examined. To bridge this gap, this study explores doctors' participation in DMIC services and its effects on their online performance, as well as its effect on patients' evaluation of them on OHC platforms.

The authors propose hypotheses based on structural holes theory. A unique dataset obtained from one of the most popular OHCs in China is used to test the hypotheses, and difference-in-differences estimation is adopted to test the causality of the relationship.

The results demonstrate that providing DMIC services improves doctors' online consultation performance and patients' evaluations of them but has no significant effect on doctors' knowledge-sharing performance on OHC platforms. Doctors' knowledge-sharing performance and consultation performance mediate the relationship between participation in DMIC services and patients' evaluation of doctors. Regarding doctors' participation in DMIC services, its impact on doctors' consultation performance and patients' evaluation of them is weaker for doctors with higher professional titles than for doctors with lower professional titles.

The findings clarify the value creation mechanisms of online collaboration between doctors and medical institutions and thereafter facilitate doctors' participation in DMIC services and enhance the sustainable development of OHCs.

The purpose of this paper is to propose a new approach to retrieve similar questions in online health communities to improve the efficiency of health information retrieval and sharing.

This paper proposes a hybrid approach to combining domain knowledge similarity and topic similarity to retrieve similar questions in online health communities. The domain knowledge similarity can evaluate the domain distance between different questions. And the topic similarity measures questions’ relationship base on the extracted latent topics.

The experiment results show that the proposed method outperforms the baseline methods.

This method conquers the problem of word mismatch and considers the named entities included in questions, which most of existing studies did not.

Previous dynamic prediction models rarely handle multi-period data with different intervals, and the large-scale patient hospital records are not effectively used to improve the prediction performance. This paper aims to focus on the prediction of cardiovascular disease using the improved long short-term memory (LSTM) model.

A new model based on the traditional LSTM was proposed to predict cardiovascular disease. The irregular time interval is smoothed to obtain the time parameter vector, and it is used as the input of the forgetting gate of LSTM to overcome the prediction obstacle caused by the irregular time interval.

The experimental results show that the dynamic prediction model proposed in this paper obtained a significant better classification performance compared with the traditional LSTM model.

In this paper, the authors improved the LSTM by smoothing the irregular time between different medical stages of the patient to obtain the temporal feature vector.

Although the use of instant messaging (IM) at work has been studied in the IS field, its effective use and impact on performance have not been adequately addressed. The purpose of this paper is to explore the antecedents and consequences of the effective use of IM at work by adapting Burton-Jones and Grange’s theory of effective use.

The authors introduce “Comprehensive IM policy” as a facilitator of adaptation and learning actions to improve the effective use of IM, which will improve communication quality and productivity. The impact of IM competence on effective use is also discussed. Based on a survey of 215 managers, this study applies the partial least square technique to test the research model.

The results indicate that comprehensive IM policy encourages adaptation and learning actions, which improve the effective use of IM and thereafter improve communication quality and productivity. Meanwhile, IM competence has a substitutive interaction effect with IM reconfiguration and self-learning on effective use.

The results refine the general theory of effective use and provide managers with an approach to leverage IM use at work for performance gains.

Stock price prediction is a hot topic and traditional prediction methods are usually based on statistical and econometric models. However, these models are difficult to deal with nonstationary time series data. With the rapid development of the internet and the increasing popularity of social media, online news and comments often reflect investors’ emotions and attitudes toward stocks, which contains a lot of important information for predicting stock price. This paper aims to develop a stock price prediction method by taking full advantage of social media data.

This study proposes a new prediction method based on deep learning technology, which integrates traditional stock financial index variables and social media text features as inputs of the prediction model. This study uses Doc2Vec to build long text feature vectors from social media and then reduce the dimensions of the text feature vectors by stacked auto-encoder to balance the dimensions between text feature variables and stock financial index variables. Meanwhile, based on wavelet transform, the time series data of stock price is decomposed to eliminate the random noise caused by stock market fluctuation. Finally, this study uses long short-term memory model to predict the stock price.

The experiment results show that the method performs better than all three benchmark models in all kinds of evaluation indicators and can effectively predict stock price.

In this paper, this study proposes a new stock price prediction model that incorporates traditional financial features and social media text features which are derived from social media based on deep learning technology.

Firms invest much money in information technology (IT) since IT support has been recognized as a critical enabler of employee outcomes. However, the value obtained by organizations and their employees is not always as much as they anticipated because of, at least partly, a poor relationship between IT staff and users. The purpose of this paper is to apply the social capital theory to examine relationship management between IT and business and explores mechanisms through which social capital between IT staff and users affect users’ employee outcomes, including job satisfaction and job performance.

Based on social capital theory and past literature, the researchers propose a research model and explore the effect of social capital on knowledge sharing, IT users’ perceived service quality, job satisfaction and ultimately job performance. Based on a survey of 289 respondents, this study applies the partial least square technique to test the research model.

Mediation test was performed to explore the effect mechanisms of social capital on employee outcomes, and the results indicate that three dimensions of social capital affect IT users’ job satisfaction and job performance in different approaches.

This study uses social capital theory to direct how to improve the poor relationship between IT staff and users and provides a useful insight into the mechanisms through which three dimensions of social capital improve users’ job satisfaction and job performance.

The literature reports inconsistent findings about the effects of social media usage (SMU). Researchers distinguish between active and passive social media usage (ASMU and PSMU), which can generate different effects on users by social support and social comparison mechanisms, respectively. Drawing on social presence theory (SPT), this study integrates an implicit social presence mechanism with the above two mechanisms to explicate the links between SMU and seniors' loneliness.

Data were collected from a field study by interviewing seniors living in eight aging care communities in China. Loneliness, social media activities and experiences with social media in terms of online social support (OSS), upward social comparison (USC) and social presence (SP) were assessed. Factor-based structural equation modeling was used to analyze the data.

OSS can mediate the relationship between ASMU and seniors' loneliness. Moreover, SP mediates between ASMU, PSMU, and seniors' loneliness, and between OSS, USC and seniors' loneliness. OSS mediates the relationship between ASMU and SP, and USC mediates the relationship between PSMU and SP.

This study shows that social media can alleviate seniors' loneliness, which could help relieve the pressures faced by health and social care systems. Social presence features are suggested to help older users interact with social health technologies in socially meaningful ways.

This study not only demonstrates that SP can play a crucial role in the relationship between both ASMU and PSMU and loneliness, but also unravels the links between SP and OSS, as well as USC.