Online meta-learning for POI recommendation

Lv, Yao; Sang, Yu; Tai, Chong; Cheng, Wei; Shang, Jedi S.; Qu, Jianfeng; Chu, Xiaomin; Zhang, Ruoqian

doi:10.1007/s10707-021-00459-6

Cited by 5 publications

(2 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…During the learning process, the teacher observes and analyzes the questions raised by students about their surrounding environment and summarizes them into individual knowledge points. Then, based on this information, it is recommended to students, searching for teaching videos posted by teachers who have studied this lesson on the internet for students to download and watch, to better understand the knowledge points [19][20]. As shown in Figure 3, the composition of online self-directed learning platforms for college students mainly includes school education network centers, professional websites, official corporate websites and others.…”

Section: Recommended Algorithm For E-learningmentioning

confidence: 99%

Current Situation Dissection and Ability Cultivation Strategies of Online Autonomous Learning for College Students

2023

aetp

View full text Add to dashboard Cite

With the progress of society, college students have a strong demand for new media technologies such as the internet, digitization and information resources, which has led to the formation of autonomous learning models in the internet environment. This article aimed to study the cultivation strategies of online autonomous learning ability for college students. Through the investigation of the online learning platform, the problems existing in the current situation and their influencing factors could be understood. Then the hypothesis was verified based on the theoretical model, constructing the model for practical application effectiveness testing. Finally, based on the data results, a preliminary summary was made that the participation rate of college students in online extracurricular expansion classes was not very high, basically maintaining between 73% and 78%. However, due to the rich and diverse online courses, most students were able to actively communicate and exchange with teachers. What they need to do was how to access the internet and use online platforms to acquire and internalize knowledge. This indicated that most students have mastered the ways to acquire knowledge on online platforms and had a high level of understanding of them.

show abstract

Section: Recommended Algorithm For E-learningmentioning

confidence: 99%

Current Situation Dissection and Ability Cultivation Strategies of Online Autonomous Learning for College Students

2023

aetp

View full text Add to dashboard Cite

show abstract

“…With the continuous development of internet technology, users may leave their check-in location information in different places [1] [2]. Based on these check-in location information, recommendation algorithms can not only recommend tourist attractions that may be interested in to users, but also effectively help businesses recommend their information to target users.…”

Section: Introductionmentioning

confidence: 99%

Exploring Diversity and Time-aware Recommendations: A LSTM-DNN Model with Bidirectional DTW Algorithm

Li,

Chen,

Sun

et al. 2023

Preprint

View full text Add to dashboard Cite

With the advent of the Web 3.0 era, the number and types of data in the network have sharply increased, and the application scenarios of recommendation algorithms have also been expanded to a certain extent. Location recommendation has gradually become one of the popular application scenarios in recommendation algorithms. Traditional recommendation algorithms not only ignore the time attribute of data when recommending information to users, but also blindly pursue the recommendation accuracy, which will cause certain "information cocoon room" problems. Therefore, this article treats user historical data as a time series and proposes a LSTM-DNN model based on the bidirectional DTW algorithm. Firstly, in response to the issue of different users consuming different amounts of information, this article proposes a bidirectional DTW algorithm to calculate the similarities between different users. Secondly, this article supplements the user dataset from three perspectives: "utilization" of information, "exploration", and spatiotemporal attributes of data, which alleviates the problem of data sparsity and cold start in the dataset to a certain extent. Moreover, it effectively enhances the diversity of recommendation results. Finally, this paper constructs a LSTM-DNN neural network to dynamically obtain user interests and preferences, and proposes a new metric CSSD to measure the diversity of algorithm recommendation results. Experiments have shown that the model effectively enhances the diversity of recommendation results while ensuring recommendation accuracy.

show abstract