Neural Matrix Factorization Recommendation for User Preference Prediction Based on Explicit and Implicit Feedback

Explicit feedback and implicit feedback are two important types of heterogeneous data for constructing a recommendation system. The combination of the two can effectively improve the performance of the recommendation system. However, most of the current deep learning recommendation models fail to fully exploit the complementary advantages of two types of data combined and usually only use binary implicit feedback data. Thus, this paper proposes a neural matrix factorization recommendation algorithm (EINMF) based on explicit-implicit feedback. First, neural network is used to learn nonlinear feature of explicit-implicit feedback of user-item interaction. Second, combined with the traditional matrix factorization, explicit feedback is used to accurately reflect the explicit preference and the potential preferences of users to build a recommendation model; a new loss function is designed based on explicit-implicit feedback to obtain the best parameters through the neural network training to predict the preference of users for items; finally, according to prediction results, personalized recommendation list is pushed to the user. The feasibility, validity, and robustness are fully demonstrated in comparison with multiple baseline models on two real datasets.

Predicting Activation Liking of People With Dementia

Physical, social and cognitive activation is an important cornerstone in non-pharmacological therapy for People with Dementia (PwD). To support long-term motivation and well-being, activation contents first need to be perceived positively. Prompting for explicit feedback, however, is intrusive and interrupts the activation flow. Automated analyses of verbal and non-verbal signals could provide an unobtrusive means of recommending suitable contents based on implicit feedback. In this study, we investigate the correlation between engagement responses and self-reported activation ratings. Subsequently, we predict ratings of PwD based on verbal and non-verbal signals in an unconstrained care setting. Applying Long-Short-Term-Memory (LSTM) networks, we can show that our classifier outperforms chance level. We further investigate which features are the most promising indicators for the prediction of activation ratings of PwD.

What is left after an error? Towards a comprehensive account of goal-based binding and retrieval

The cognitive system readily detects and corrects erroneous actions by establishing episodic bindings between representations of the acted upon stimuli and the intended correct response. If these stimuli are encountered again, they trigger the retrieval of the correct response. Thus, binding and retrieval efficiently pave the way for future success. The current study set out to define the role of the erroneous response itself and explicit feedback for the error during these processes of goal-based binding and retrieval. Two experiments showed robust and similar binding and retrieval effects with and without feedback and pointed towards sustained activation of the unbound, erroneous response. The third experiment confirmed that the erroneous response is more readily available than a neutral alternative. Together, the results demonstrate that episodic binding biases future actions toward success, guided primarily through internal feedback processes, while the erroneous response still leaves detectable traces in human action control.

A Top-N Movie Recommendation Framework Based on Deep Neural Network with Heterogeneous Modeling

To provide more accurate and stable recommendations, it is necessary to combine display information with implicit information and to dig out potential information. Existing methods only consider explicit feedback information or implicit feedback information unilaterally and ignore the potential information of explicit feedback information and implicit feedback information, which is also crucial to the accuracy of the recommendation system. However, the traditional Heterogeneous Information Networks (HIN) recommendation ignores the attribute information in the meta-path and the interaction between the user and the item and, instead, only considers the linear characteristics of the user-object often ignoring its non-linear characteristics. Aiming at the potential information acquisition problem from assorted feedback, we propose a new top-N recommendation method MFDNN for Heterogeneous Information Networks (HINs). First, we consider explicit and implicit feedback information to determine the potential preferences of users and the potential features of the product. Then, matrix factorization (MF) and a deep neural network (DNN) are fused to learn independent feature embeddings through MF and DNN, and fully considering the linear and non-linear characteristics of the user-object. MFDNN was tested on several real data sets, such as Movie-Lens, and compared with benchmark experiments. MFDNN significantly improved the hit ratio (HR) and normalized discounted cumulative gain (NDCG). Further research showed that the meta-path bias had an excellent effect on the gain of potential information mining and the fusion of explicit and implicit information in the accuracy and stability of user interest classification.

Holistic Transfer to Rank for Top-N Recommendation

Recommender systems have been a valuable component in various online services such as e-commerce and entertainment. To provide an accurate top-N recommendation list of items for each target user, we have to answer a very basic question of how to model users’ feedback effectively. In this article, we focus on studying users’ explicit feedback, which is usually assumed to contain more preference information than the counterpart, i.e., implicit feedback. In particular, we follow two very recent transfer to rank algorithms by converting the original feedback to three different but related views of examinations, scores, and purchases, and then propose a novel solution called holistic transfer to rank (HoToR), which is able to address the uncertainty challenge and the inconvenience challenge in the existing works. More specifically, we take the rating scores as a weighting strategy to alleviate the uncertainty of the examinations, and we design a holistic one-stage solution to address the inconvenience of the two/three-stage training and prediction procedures in previous works. We then conduct extensive empirical studies in a direct comparison with the two closely related transfer learning algorithms and some very competitive factorization- and neighborhood-based methods on three public datasets and find that our HoToR performs significantly better than the other methods in terms of several ranking-oriented evaluation metrics.

Re-Enrichment Learning: Metadata Saliency for the Evolutive Personalization of a Recommender System

Many studies have been conducted on recommender systems in both the academic and industrial fields, as they are currently broadly used in various digital platforms to make personalized suggestions. Despite the improvement in the accuracy of recommenders, the diversity of interest areas recommended to a user tends to be reduced, and the sparsity of explicit feedback from users has been an important issue for making progress in recommender systems. In this paper, we introduce a novel approach, namely re-enrichment learning, which effectively leverages the implicit logged feedback from users to enhance user retention in a platform by enriching their interest areas. The approach consists of (i) graph-based domain transfer and (ii) metadata saliency, which (i) find an adaptive and collaborative domain representing the relations among many users’ metadata and (ii) extract attentional features from a user’s implicit logged feedback, respectively. The experimental results show that our proposed approach has a better capacity to enrich the diversity of interests of a user by means of implicit feedback and to help recommender systems achieve more balanced personalization. Our approach, finally, helps recommenders improve user retention, i.e., encouraging users to click more items or dwell longer on the platform.

THE EFFECTS OF IMPLICIT AND EXPLICIT CLASSROOM FEEDBACK ON BILINGUAL SPEECH PRODUCTION

Recent research on the role of classroom feedback has pointed out that learning is easier and quicker when students receive detailed feedback that tells them precisely what they have done wrong and what they should have done instead. Our study aimed to investigate how two different types of classroom feedback influence the development of bilingual oral production. Fifty-four English L2 learners were divided into an experimental group and a control group. Both groups were exposed to a two-month-hybrid experience for the development of oral production. The control group received implicit feedback based on the general content of their oral production. The experimental group received explicit feedback based on grammar, pointing out corrections in relation to the form of their oral production. Through a pre- and post-test, we verified whether the different types of feedback impacted the participants' oral production, in terms of grammatical accuracy, weighted lexical density and fluency. Results show that explicit feedback was more effective in improving learner´s L2 grammatical accuracy after the two months of intervention. However, there were no significant differences between the two types of feedback in relation to developing lexical density or fluency over time.

Perbandingan Interpretasi Analisis Data Page View dan Click Related Post Pada Website Edukasi Sebagai Implisit Feedback Dengan Hasil Interpretasi Penggunaan Teknologi EyeTracking

The analysis used in this study uses the help of Google Analytics to understand how the user's behavior on the Calculus learning material educational website page. Are users interested in recommendation articles? The answer to this question provides insight into the user's decision process and suggests how far a click is the result of an informed decision. Based on these results, it is hoped that a strategy to generate feedback from clicks should emerge. To evaluate the extent to which feedback shows relevance, versus implicit feedback to explicit feedback collected manually. The study presented in this study differs in at least two ways from previous work assessing the reliability of implicit feedback. First, this study aims to provide detailed insight into the user decision-making process through the use of a recommendation system with an implicit feedback feature. Second, evaluate the relative preferences that come from user behavior (user behavior). This differs from previous studies which primarily assessed absolute feedback.

Roles of Feedback to English Writing Improvement: Thai EFL Novice Writers in Higher Education

Writing has been the most difficult skill among EFL students for several decades. It inevitably promotes writing feedback and approaches to English writing classroom to minimize students’ errors in their writing draft revision. Hereby, the current study aimed at investigating perceptions towards the three writing features: vocabulary, grammar, and content, and examining the differences of the three assessments including teacher feedback, peer feedback, and self-correction. In addition, the teacher feedback preference as implicit and explicit feedback was determined as well. Participants were 32 first-year undergraduate students majoring in English for International Communication at Rajamangala University of Technology, Lanna Tak, Thailand. The current study employed a mixed-method research approach. Questionnaires and open-ended questions were utilized as research tools. Participants were assigned three genres of writing paragraphs. It took 15 consecutive weeks in providing three different feedback to purposive samples. For every assignment, their peers corrected their first drafts and then they rechecked and edited their output by their own decision. Afterward, the teacher provided both implicit and explicit feedback on the revision process. The data obtained were quantitatively analyzed for mean, standard deviation, and a paired sample t-test which have been deployed to the differences among the three feedback. Correspondingly, all written responses were thematically grouped and transcribed into frequency and percentage. The findings indicated that students mostly expected the teacher to edit their misused words, grammatical errors, and ideas on their drafts. As for the three feedback, most beginning writers particularly believed that teacher feedback, which was followed by self-correction and peer feedback, was much necessary for writing improvement and teachers should edit their redrafts explicitly in an EFL writing classroom.