BackgroundLow survey response rates in general practice are common and lead to loss of power, selection bias, unexpected budgetary constraints and time delays in research projects.MethodsObjective: To assess the effectiveness of recruitment strategies aimed at increasing survey response rates among GPs.Design: Systematic review.Search methods: MEDLINE (OVIDSP, 1948-2012), EMBASE (OVIDSP, 1980-2012), Evidence Based Medicine Reviews (OVIDSP, 2012) and references of included papers were searched. Major search terms included GPs, recruitment strategies, response rates, and randomised controlled trials (RCT).Selection criteria: Cluster RCTs, RCTs and factorial trial designs that evaluate recruitment strategies aimed at increasing GP survey response rates.Data collection and analysis: Abstracts identified by the search strategy were reviewed and relevant articles were retrieved. Each full-text publication was examined to determine whether it met the predetermined inclusion criteria. Data extraction and study quality was assessed by using predetermined checklists.ResultsMonetary and nonmonetary incentives were more effective than no incentive with monetary incentives having a slightly bigger effect than nonmonetary incentives. Large incentives were more effective than small incentives, as were upfront monetary incentives compared to promised monetary incentives. Postal surveys were more effective than telephone or email surveys. One study demonstrated that sequentially mixed mode (online survey followed by a paper survey with a reminder) was more effective than an online survey or the combination of an online and paper survey sent similtaneously in the first mail out. Pre-contact with a phonecall from a peer, personalised packages, sending mail on Friday, and using registered mail also increased response rates in single studies. Pre-contact by letter or postcard almost reached statistical signficance.ConclusionsGP survey response rates may improve by using the following strategies: monetary and nonmonetary incentives, larger incentives, upfront monetary incentives, postal surveys, pre-contact with a phonecall from a peer, personalised packages, sending mail on Friday, and using registered mail. Mail pre-contact may also improve response rates and have low costs. Improved reporting and further trials, including sequential mixed mode trials and social media, are required to determine the effectiveness of recruitment strategies on GPs' response rates to surveys.
In recent years, along with the dramatic developments of deep learning in the natural language processing (NLP) domain, there are notable multilingual pre-trained language techniques have been proposed. These recent multilingual text analysis and mining models have demonstrated state-of-the-art performances in several primitive NLP's tasks including cross-lingual text classification (CLC). However, these recent multilingual pre-trained language models still suffered limitations which are involved in the simplicity to be adapted for specific task-driven fine-tuning in the context of low-resource languages. Moreover, they also encountered problems related to the capability of preserving the global semantic (e.g., topic, etc.) and long-range relationships between words to better fine-tune for effectively handling cross-lingual text classification task. To meet these challenges, in this paper, we proposed a novel topic-driven multi-typed text graph attention-based representation learning method for dealing with cross-lingual text classification problem, called as: TG-CTC. In our proposed TG-CTC model, we utilize a novel fused topic-driven multi-typed text graph representation to jointly learn the rich-schematic structural and global semantic information of texts to effectively fulfill the CLC task. In more specifics, we integrate the heterogeneous text graph attention network (GAT) with the neural topic modelling approach to enrich the semantic information of learnt textual representations in context of multi-language. Extensive experiments in benchmark multilingual datasets showed the effectiveness of our proposed TG-CTC model in comparing with the contemporary state-of-the-art baselines.
Recent advanced deep learning architectures, such as neural seq2seq, transformer, etc. have demonstrated remarkable improvements in multi-typed sentiment classification tasks. Even though recent transformerbased and seq2seq-based models have successfully enabled to capture rich-contextual information of texts, they are still lacking of attention on incorporating the global semantic information, such as topic, in order to sufficiently leverage the performance of downstream SA task. Moreover, emotional expressions of users are normally in forms of natural human-written textual data which might consist a lot of noise and ambiguity which impose great challenges on the processes of textual representation learning as well as sentiment polarity prediction. To meet these challenges, we propose a novel integrated fuzzy-neural architecture with a topic-driven textual representation learning approach for handling SA task, called as: TopFuzz4SA. Specifically, in the proposed TopFuzz4SA model, we first apply a topic-driven neural encoder-decoder architecture with the incorporation of latent topic embedding and attention mechanism to sufficiently learn both rich contextual and global semantic information of the given textual data. Then, the achieved rich semantic representations of texts are fed into a fused deep fuzzy neural network to effectively reduce the feature ambiguity and noise, forming the final textual representations for sentiment classification task. Extensive experiments in benchmark datasets demonstrate the effectiveness of our proposed TopFuzz4SA model in comparing with contemporary state-of-the-art baselines.
Recent KG-oriented recommendation techniques mainly focus on the direct interaction between entities in the given KGs as the rich information sources for leveraging the quality of recommendation outputs. However, they are still hindered by the heterogeneity, type-varied entities and their relationships in knowledge graphs (KG) as the heterogeneous information networks (HIN). This limitation seems challenging to build up an effective approach for the KG-based recommendation system in both semantic path-based exploitation and heterogeneous information extraction. To meet these challenges, we proposed a novel integrated HIN embedding with reinforcement learning (RL)-based feature engineering for recommendation, called as: HINRL4Rec. First of all, we apply the combined textual meta-path-based embedding approach for learning multiple-rich-schematic representations of user/item and their associated entities. Then, these extracted multi-typed embeddings of user and item entities are fused into the unified embedding spaces during the KG embedding process. Finally, the unified representations of users and items are then used to facilitate the RL-based policy-driven searching process in the next steps for performing the recommendation task. Extensive experiments in real-world datasets demonstrate the effectiveness of our proposed model in comparing with recent state-of-the-art recommendation baselines.
Recently, many pre-trained text embedding models have been applied to effectively extract latent features from texts and achieve remarkable performance in various downstream tasks of sentiment analysis domain. However, these pre-trained text embedding models also encounter limitations related to the capability preserving the syntactical structure as well as the global long-range dependent relationships of words. Thus, they might fail to recognize the relevant syntactical features of words as valuable evidences for analyzing sentiment aspects. To overcome these limitations, we proposed a novel deep semantic contextual embedding technique for sentiment analysis, called as: SE4SA. Our proposed SE4SA is a multi-level text embedding model which enables to jointly exploit the long-range syntactical and sequential representations of texts. Then, these achieved rich semantic textual representations can support to have a better understanding on the sentiment aspects of the given text corpus, thereby resulting the better performance on sentiment analysis task. Extensive experiments in several benchmark datasets demonstrate the effectiveness or our proposed SE4SA model in comparing with recent state-of-the-art model.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.