No abstract

Purpose – The purpose of this paper is to investigate the role of trust management on the fundraising performance in reward-based crowdfunding. Design/methodology/approach – A research model was constructed based on elaboration likelihood model (ELM) and literatures with five hypotheses developed. Data were collected from www.demohour.com - the first and one of the largest reward-based crowdfunding platforms in China. In total, 829 reward-based crowdfunding projects were analyzed to test hypotheses. To test the hypotheses, partial least squares was used to analyze data of entrepreneur/sponsor profiles, entrepreneur/sponsor behaviors, and crowdfunding projects. Findings – Results indicated trust management significantly promoted fundraising performance via central (entrepreneur’s creditworthiness) and peripheral (entrepreneur-sponsor interactions) routes. The peripheral route (entrepreneur-sponsor interaction) showed significantly higher effects than the central route (entrepreneur’s creditworthiness). The finding aligns with authors’ assumptions derived from unique characteristics of reward-based crowdfunding – community and collaboration because personal, dynamic message interactions were more effective than static, historical success records on the trust establishment. In addition to the main effects, the results also showed entrepreneur’s prior success crowdfunding records positively moderated the effect of entrepreneur-sponsor interaction on fundraising performance. Originality/value – This study is the first paper that reveals the value of trust management in reward-based fundraising, especially the effect of dynamic entrepreneur-sponsor message interactions. Entrepreneur-sponsor interactions not only promoted community benefits in crowdfunding, but also cultivated trust relationships between entrepreneurs and sponsors. Previous studies mainly focussed on the entrepreneur’s popularity level on third-party social media (such as Facebook) toward fundraising performance. This study examines the effect of direct entrepreneur-sponsor interactions on the crowdfunding platform. Additionally, this study found one moderating effect from the central route to the peripheral route. It is a rare case in studies based on ELM. Finally, this study demonstrates how to incorporate a theoretical framework guiding the analysis of structured and unstructured data for in-depth analysis, result interpretation, and corresponding intervention strategy development.

PurposeCritical thinking is considered important in psychological science because it enables students to make effective decisions and optimizes their performance. Aiming at the challenges and issues of understanding the student's critical thinking, the objective of this study is to analyze online discussion data through an advanced multi-feature fusion modeling (MFFM) approach for automatically and accurately understanding the student's critical thinking levels.Design/methodology/approachAn advanced MFFM approach is proposed in this study. Specifically, with considering the time-series characteristic and the high correlations between adjacent words in discussion contents, the long short-term memory–convolutional neural network (LSTM-CNN) architecture is proposed to extract deep semantic features, and then these semantic features are combined with linguistic and psychological knowledge generated by the LIWC2015 tool as the inputs of full-connected layers to automatically and accurately predict students' critical thinking levels that are hidden in online discussion data.FindingsA series of experiments with 94 students' 7,691 posts were conducted to verify the effectiveness of the proposed approach. The experimental results show that the proposed MFFM approach that combines two types of textual features outperforms baseline methods, and the semantic-based padding can further improve the prediction performance of MFFM. It can achieve 0.8205 overall accuracy and 0.6172 F1 score for the “high” category on the validation dataset. Furthermore, it is found that the semantic features extracted by LSTM-CNN are more powerful for identifying self-introduction or off-topic discussions, while the linguistic, as well as psychological features, can better distinguish the discussion posts with the highest critical thinking level.Originality/valueWith the support of the proposed MFFM approach, online teachers can conveniently and effectively understand the interaction quality of online discussions, which can support instructional decision-making to better promote the student's knowledge construction process and improve learning performance.