Search results

English original movies played an important role in English learning and communication. In order to find the required movies for us from a large number of English original movies and reviews, this paper proposed an improved deep reinforcement learning algorithm for the recommendation of movies. In fact, although the conventional movies recommendation algorithms have solved the problem of information overload, they still have their limitations in the case of cold start-up and sparse data.

To solve the aforementioned problems of conventional movies recommendation algorithms, this paper proposed a recommendation algorithm based on the theory of deep reinforcement learning, which uses the deep deterministic policy gradient (DDPG) algorithm to solve the cold starting and sparse data problems and uses Item2vec to transform discrete action space into a continuous one. Meanwhile, a reward function combining with cosine distance and Euclidean distance is proposed to ensure that the neural network does not converge to local optimum prematurely.

In order to verify the feasibility and validity of the proposed algorithm, the state of the art and the proposed algorithm are compared in indexes of RMSE, recall rate and accuracy based on the MovieLens English original movie data set for the experiments. Experimental results have shown that the proposed algorithm is superior to the conventional algorithm in various indicators.

Applying the proposed algorithm to recommend English original movies, DDPG policy produces better recommendation results and alleviates the impact of cold start and sparse data.

Cultivating loyal customers is a pressing concern for streamers. The present study investigates how to build interpersonal relationships with streamers and whether different interpersonal relationship factors lead to repurchase intention and WOM intention in live streaming commerce. The moderating effect of gender is also examined.

A self-administered questionnaire was completed by 429 live streaming commerce users in mainland China. Partial least squares structural equation modeling was used to test the research hypotheses.

The results indicate that all four streamer attributes (expertise, authenticity, attractiveness, and homophily) have a positive influence on swift guanxi, and swift guanxi is effective in predicting both calculative commitment and affective commitment. In addition, all interpersonal relationship factors (swift guanxi, calculative commitment, and affective commitment) significantly affect repurchase intentions, with only affective commitment being linked to WOM intention. Also, the moderating role of gender was confirmed in expertise – swift guanxi, attractiveness – swift guanxi, cognitive commitment – repurchase intention and affective commitment – repurchase intention linkages.

This paper contributes to the live streaming commerce literature by integrating swift guanxi, calculative commitment, and affective commitment to understand the repurchase intention and WOM intention from the relationship-building process perspective. In addition, this paper enriches the source credibility and source attractiveness models by identifying gender boundaries on the effectiveness of these models in predicting swift guanxi.

Based on the computers as social actors (CASA) theory, this study aims to explore the impact of three characteristics of virtual influencers (conversational tone, autonomy and responsiveness) on social presence, telepresence and customer engagement.

Using the purposive sampling technique, online survey was administered to Chinese Gen-Z consumers engaging with virtual influencers. Subsequently, 357 respondents were sampled. SPSS 29.0 and Smart PLS 4.0 were used to perform the analyses.

The results show that conversational tone and responsiveness have significant positive effects on both social presence and telepresence. Autonomy has a positive effect on telepresence, but not social presence. Social presence and telepresence have a positive impact on customer engagement.

As a burgeoning field, there is still uncertainty among both practitioners and researchers about the methods that virtual influencers engage their users in the context of social media. Limited research has focused on presence (social presence and telepresence) due to virtual influencers. Therefore, the CASA theory offers valuable insights into how virtual influencers’ characteristics contribute to the presence and customer engagement and provides practical guidance for the design of virtual influencers.

The study aims to determine the impact of sustainable manufacturing on environmental performance through government regulation and eco-innovation in Indonesian small and medium-sized enterprises (SMEs).

The results indicate sustainable manufacturing plays a significant role in SMEs' environmental performance and regulations, and eco-innovation can moderate it. It also reveals that government regulation has a positive and significant effect on environmental performance. Moreover, eco-innovation has a positive and significant effect on environmental performance.

The findings of this study indicate that SMEs can embrace sustainable manufacturing practices and achieve their long-term sustainability goals by adhering to regulations, collaborating with stakeholders and implementing eco-friendly innovations.

This research uncovers ground-breaking perspectives on the evolution of scientific knowledge about the impact of eco-innovation, regulatory measures and sustainable manufacturing practices on the environmental performance of SMEs.