Learning User Preference Patterns for Top-N Recommendations

Recommender systems play an important role in most modern e-commerce applications. They have allowed users to become aware of the myriad choices available to them. The ease of information and the abundance of options have helped users make educated decisions. A recommender system studies a user's preferences and continues learning the user's changing interests, so as to suggest items that incline with the user's interests. In cases where a user is new to the application, or the user prefers not to discourse preferences, the recommender system is unable to gather the user's preference on any item. This is called the cold start problem; wherein the system can make valid recommendations only once the user starts informing the system about his/her choices. In this paper, we discuss the challenges faced by the cold start problem and how this problem may be alleviated using social media. We suggest an approach where we collect public information from users' social media accounts and analyze this information to understand their preferences. In particular, we gather the new user's information using their Twitter profile; i.e., the user's interest and preferences are extracted from his/her Twitter profile by analyzing his/her tweets. These interests will help the system understand what kind of movies the user will be most interested in. We compare these preferences with the metadata about the individual items. Using this approach, we develop a movie recommendation system wherein we produce top-N movie recommendations for a user. We used the MovieTweetings dataset to model the application. Two sets of results have been produced. In the first, smaller set of 770 users, 72.67% of users have received 100% accurate movie recommendations while nearly 80% of users got more than 75% accuracy. For the second, larger set of more than 3,500 users, 53 % of users have received 100% accurate recommendations while 72% of users got more than 75% accuracy. These encouraging results have demonstrated that the approach is effectively in alleviating cold start problems in recommendation systems, and may be applicable to many other e-commerce applications.

The primary goal of a recommender system is to generate high quality user-centred recommendations. However, the traditional evaluation methods and metrics were developed before researchers understood all the factors that increase user satisfaction. This study is an introduction to a novel user and item classification framework. It is proposed that this framework should be used during user-centred evaluation of recommender systems and the need for this framework is justified through experiments. User profiles are constructed and matched against other users’ profiles to formulate neighbourhoods and generate top-N recommendations. The recommendations are evaluated to measure the success of the process. In conjunction with the framework, a new diversity metric is presented and explained. The accuracy, coverage, and diversity of top-N recommendations is illustrated and discussed for groups of users. It is found that in contradiction to common assumptions, not all users suffer as expected from the data sparsity problem. In fact, the group of users that receive the most accurate recommendations do not belong to the least sparse area of the dataset.

Currently, the research on recommend system has drawn intensive attention from many researchers. However, it is still a concerned focus to make accurate recommendations in a short time period. Recently, some researchers have proposed a formal model based on learning to rank for Top-N recommendation. Aiming at improving the effect of Top-N recommendation and solving the problem of timeliness, we analyze and summarize out some factors that affect the timeliness of recommendation, and propose a ranking model of recent feedback which combined with online learning. Experimental results show that after the second ranking of users' recent feedback and basic recommendation output, the recommendation accuracy is improved effectively. Furthermore, we also explores the application of online learning algorithm based on the ranking model of recent feedback. The simulation experiments show that the model can still perform an accurate recommendation after being updated online in real time.

To enhance students’ English writing ability, English creative writing has become a common course offered by colleges and universities. English reference is an indispensable tool for creative English writing. How to choose appropriate English references is an important guarantee to complete good work. Therefore, this paper proposes a Deep Semantic Mining-based Recommendation (DSMR) algorithm for English writing reference selection and recommendation to assist the completion of high-quality English creative writing works. The model can extract user features and document attributes more accurately by deeply mining semantic information of literature content and user needs, so as to achieve more accurate recommendations. First, the Bidirectional Encoder Representation from Transformers (BERT) pretraining model is adopted to process literature content and user requirement documents. Through in-depth mining of user characteristics and literature attributes, the problems of data sparsity and cold start of items are effectively alleviated. Then, the forward long short-term memory (LSTM) network was used to focus on the changes in user preferences over time, resulting in more accurate recommendations. The experimental results show that the use of heterogeneous information can significantly improve the recommendation performance, and the additional use of user attribute information can also improve the recommendation performance. Compared with other benchmark models, the recommendation quality of this model is greatly improved.

Collaborative Filtering Recommender Systems are used to recommend items that may match each user preference on the basis of preferences of similar users in the system. Since different users have different patterns of preference, there is a problem when one user's preference is used to recommend another user's preference. A way of converting one user's preference pattern into another user's pattern is proposed. However, there are several problems with current methods: some methods take many users' patterns as a similar one, some rely on co-rated items data between user pairs which is hardly obtained, and some methods can't exactly convert a rating to a suitable one. This work proposes a new transpose function that can be utilized on any pair of users regardless of using co-rated items by applying latent model. The new transpose function is composed of an original value term and an adjustment term which transposes an original rating to an average of the target user's rating on the corresponding items. Moreover, for more accuracy, a distribution term and a confidence term are combined to the adjustment term. This new function provides better results than the current transpose function in terms of three evaluation metrics (MAE, F-measure, and coverage).

One of the most important challenges for improving personalized services in industries like tourism is predicting users’ near-future movements based on prior behavior and current circumstances. Next POI (Point of Interest) recommendation is essential for helping users and service providers by providing personalized recommendations. The intricacy of this work, however, stems from the requirement to take into consideration several variables at once, such as user preferences, time contexts, and geographic locations. POI selection is also greatly influenced by elements like a POI’s operational status during desired visit times, desirability for visiting during particular seasons, and its dynamic popularity over time. POI popularity is mostly determined by check-in frequency in recent studies, ignoring visitor volumes, operational constraints, and temporal dynamics. These restrictions result in recommendations that are less than ideal and do not take into account actual circumstances. We propose the Seasonal and Active hours-guided Graph-Enhanced Transformer (SEAGET) model as a solution to these problems. By integrating variations in the seasons, operational status, and temporal dynamics into a graph-enhanced transformer framework, SEAGET capitalizes on redefined POI popularity. This invention gives more accurate and context-aware next POI predictions, with potential applications for optimizing tourist experiences and enhancing location-based services in the tourism industry.

User preferences are dynamically changing due to a variety of factors. Therefore, how to effectively extract the user's current preferences and accurately predict subsequent user preferences is one of the keys to improving service recommendation. This paper proposes a deep learning-based user preference prediction method, which combines user dynamic preference extraction and preference prediction. Firstly, the time-series LDA model is used to extract the user dynamic preference, then the LSTM neural network method is used to predict the user's preference of next time slice based on the user dynamic preference sequence. Finally, services are recommended to users based on predicted preference. The experimental results on real-world dataset show that the prediction performance of Time-aware-gate LSTM is slightly better than traditional LSTM, and the recommendation performance of the recommendation algorithm that takes preference prediction into account is better than those without preference prediction.

Estimation for the number of components in a mixture model using stepwise split-and-merge EM algorithm

Recommending new items to users remains a challenge due to the absence of user's past preferences for these items. Item features from side information are typically leveraged to tackle the problem. Existing methods formulate regression models, taking as input item features and as output user ratings. Availing of high dimensional item features, these methods are confronted with the issue of overfitting, which greatly impedes recommendation experience. In this work, we opt for feature selection to solve the problem of recommending top-N new items with high-dimensional side information. Existing feature selection methods find a common set of features for all users, which fails to differentiate user preferences over item features. To achieve personalization for feature selection, we propose to select item features specifically for users. The refined features filtered out the dimensions that are irrelevant to recommendations or unappealing to users. The experiment results on real-life datasets with high-dimensional side information reveal that the proposed method is effective in singling out features crucial to top-N recommendations and hence boosting the performance.

PurposeRecommending suitable doctors to patients on healthcare consultation platforms is important to both the patients and the platforms. Although doctor recommendation methods have been proposed, they failed to explain recommendations and address the data sparsity problem, i.e. most patients on the platforms are new and provide little information except disease descriptions. This research aims to develop an interpretable doctor recommendation method based on knowledge graph and interpretable deep learning techniques to fill the research gaps.Design/methodology/approachThis research proposes an advanced doctor recommendation method that leverages a health knowledge graph to overcome the data sparsity problem and uses deep learning techniques to generate accurate and interpretable recommendations. The proposed method extracts interactive features from the knowledge graph to indicate implicit interactions between patients and doctors and identifies individual features that signal the doctors' service quality. Then, the authors feed the features into a deep neural network with layer-wise relevance propagation to generate readily usable and interpretable recommendation results.FindingsThe proposed method produces more accurate recommendations than diverse baseline methods and can provide interpretations for the recommendations.Originality/valueThis study proposes a novel doctor recommendation method. Experimental results demonstrate the effectiveness and robustness of the method in generating accurate and interpretable recommendations. The research provides a practical solution and some managerial implications to online platforms that confront information overload and transparency issues.

Here we take advantage of the signal recovery power of Compressive Sensing (CS) to significantly reduce the computational complexity brought by the high-dimension image data, then an effective and efficient low-dimensional subspace representation of the object is computing by applying Principal Component Analysis (PCA) to a collection of object observations which are low-dimensional vectors derived from CS. An incremental PCA algorithm is used to update this subspace model for characterizing the object appearance changes. Meanwhile, two distances derived from Probabilistic Principal Component Analysis (PPCA): distance from feature space (DFFS) and distance in feature space (DIFS), are used to describe visual similarity between the learned subspace representation model and candidate targets. Comparing with the traditional used reconstruction error, the sum of two distances: DFFS + DIFS, is more accurate and more robust to noises and partial occlusions. Numerous experiment demonstrate that subspace representation model can handle the situation that target objects experience pose changes, scale changes, significant illumination variation, partial occlusions and so on.Keywordsobject trackingPPCAsubspace representation modelparticle filterdynamic modelobservation modelCompressive Sensing (CS)

Recommendation with implicit feedback has been extensively studied in recent years. It is more difficult to provide users with stable and accurate recommendation compared to recommendation with explicit feedback, due to the reason that interactions from implicit feedback datasets do not clearly indicate the level of user preference. Most existing methods dealing with implicit feedback have achieved excellent performance by focusing on other aspects rather than directly inferring user preference. In this paper, we offer accurate recommendation to users by addressing the problem of directly inferring user preference from implicit feedback with such less information and huge uncertainty. We propose a novel mixture-preference model (MPBMF), which introduces a set of pseudo-preference values to surmise the true user preference. More specifically our proposed model can be described as a Gaussian mixture model in which each single model is trained with pseudo-preferences which show the user's different views for items. Then the predicted user preference is estimated by the models under different pseudo-preferences with different contributions. We conduct extensive experiments on three real-world datasets, and the superior performance demonstrates the effectiveness of our model.

Modeling user preferences using neural networks and tensor factorization model

A natural language collaborative consultation system must take user preferences into account. A model of user preferences allows a system to appropriately evaluate alternatives using criteria of importance to the user. Additionally, decision research suggests both that an accurate model of user preferences could enable the system to improve a user's decision‐making by ensuring that all important alternatives are considered, and that such a model of user preferences must be built dynamically by observing the user's actions during the decision‐making process. This paper presents two strategies: one for dynamically recognizing user preferences during the course of a collaborative planning dialogue and the other for exploiting the model of user preferences to detect suboptimal solutions and suggest better alternatives. Our recognition strategy utilizes not only the utterances themselves but also characteristics of the dialogue in developing a model of user preferences. Our generation strategy takes into account both the strength of a preference and the closeness of a potential match in evaluating actions in the user's plan and suggesting better alternatives. By modeling and utilizing user preferences, our system is able to fulfill its role as a collaborative agent.

Typical tag recommendation systems for photos shared on social networks such as Flickr, use visual content analysis, collaborative filtering or personalization strategies to produce annotations. However, the dependence on manual intervention and the knowledge of sufficient personal preferences coupled with the folksonomic issues limit the scope of these strategies. In this paper, we present a fully automatic and folksonomically scalable tag recommendation model that can recommend tags for a user's photos without an explicit knowledge of the user's personal tagging preferences. The model is learned using the collective tagging behavior of other users in the user's local interaction network, which we believe approximates the user's preferences, at least partially. The tag recommendation model generates content-based annotations and then uses a Naive Bayes formulation to translate these annotations to a set of folksonomic tags selected from the tags used by the users in the local interaction network. Quantitative and qualitative comparisons with 890 Flickr networks show that this approach is highly useful for tag recommendation in the presence of insufficient information of a user's own preferences.