•Quality of recommendations can improve with user profile learning.•Combining novelty and popularity generates personalised recommendations.•Automatic tuning in diffusion-based methods allows better ...results on sparse data.
Recommender systems have been widely used by large companies in the e-commerce segment as aid tools in the search for relevant contents according to the user’s particular preferences. A wide variety of algorithms have been proposed in the literature aiming at improving the process of generating recommendations; in particular, a collaborative, diffusion-based hybrid algorithm has been proposed in the literature to solve the problem of sparse data, which affects the quality of recommendations. This algorithm was the basis for several others that effectively solved the sparse data problem. However, this family of algorithms does not differentiate users according to their profiles. In this paper, a new algorithm is proposed for learning the user profile and, consequently, generating personalised recommendations through diffusion, combining novelty with the popularity of items. Experiments performed in well-known datasets show that the results of the proposed algorithm outperform those from both diffusion-based hybrid algorithm and traditional collaborative filtering algorithm, in the same settings.
Seeking an efficient solution for the problem of dynamic user preferences on social networks is challenging because the input data are short texts and user preferences usually change over time. This ...work proposes a novel framework that tackles these challenges based on deep neural networks and the Dempster-Shafer theory of evidence. The framework consists of three primary phases: (1) learning the hidden space of user texts; (2) word generation and mass inference; and (3) mass combination and keyword extraction. In the first phase, user texts are grouped into small batches according to timestamps. Each batch is used for separately training two types of neural networks, the Variational Autoencoder (VAE) and the Generative Adversarial Network (GAN). In the second phase, the generators in the trained VAE and GAN work independently as two experts to generate bunches of tokens for modeling user preferences. Each bunch is considered as one piece of evidence, and is transformed into the so-called mass function in Dempster-Shafer theory by maximum a posterior estimation. In the final phase, Dempster's rule of combination is utilized for fusing the two independent pieces of evidence into an overall mass. This mass is used for extracting top keywords to form the user preferences within a specific time span. The experiments on short text datasets verified that the proposed method outperforms baseline models on many evaluation metrics. Additionally, the output of the proposed framework could be used for visualization, which is useful in many practical applications.
In recent years, E-orientation systems have played an increasingly significant role in the proposal of an academic and professional orientation to students. Research efforts have grown to provide ...more useful and effective E-orientation systems for research or other purposes. The implementation of E-orientation systems resulting from these efforts utilizes several techniques including Artificial Intelligence (AI) methodologies. This study proposes a personalised approach to support an E-orientation system that is tailored to the student’s characteristics. A key component of this system comprises an ontological model of the user profile. The objective of this research was to propose an ontology that is able to collect and analyze the user related information as well as customize the profiles with the most appropriate recommendation or orientation. The ontology employed in this study was developed using the OWL (Ontology Web Language), a knowledge representation language for authoring ontologies. In this paper we will present a definition for the user profile, and then we present our methodology of ontological modeling of the user profile, and finally the conceptual model of the user model for e-orientation systems.
Mining user data and constructing web user profiles of older adults from the perspective of elderly services is conducive to understanding their behavioral habits, needs, and usage preferences on the ...web, which provides more targeted elderly care services. In this paper, IGA-SOMK + + , which is a novel clustering method for constructing web user profiles of older adults, is proposed based on the China Family Panel Studies (CFPS) survey data, which include 6596 older adults aged greater than 60 years. The selected data aspects include basic information, work situation, health situation, living habits, and web use services. To describe the web user profiles of older adults, a hybrid method based on improved genetic algorithm (IGA) feature selection, self-organizing feature maps (SOM), and K-means + + is proposed. Data on older adults’ web use behaviors are first processed, and IGA is used for feature selection based on the adaptive crossover and mutation probabilities. SOM is then used to determine the initial center vectors of K-means + + for further clustering, which is referred to as SOMK + + (SOM-K-means + +). The results of IGA-SOMK + + are compared with those of the state-of-the-art methods, including the K-means, mini batch K-means, Agnes, K-modes, FCM, K-means + + , SOMK + + , and IHPSO-KM. In addition, the significance and robustness of IGA-SOMK + + are analyzed. The experimental results show that the IGA feature selection reduces the influence of the redundant feature factors and improves the performance of the clustering algorithm. SOMK + + overcomes the sensitivity of K-means to initial cluster centers. Moreover, IGA-SOMK + + has the best clustering effect among the compared algorithms in terms of silhouette coefficient (SC), calinski-harabaz (CH) index, and davies-bouldin (DB) metrics. For example, it increases the SC from 0.280 to 0.629. Finally, by analyzing the results, the user group of older adults is segmented to perform the deep mining of CFPS data, which verifies the feasibility of the user profile model. This paper summarizes the basic situation of the current web access of older adults in China in terms of web use services, as well as the importance of the web in their lives and in the information channels. It also provides suggestions for the current problems of older adults in accessing the web.
A tag-aware recommender system (TRS) presents the challenge of tag sparsity in a user profile. Previous work focuses on expanding similar tags and does not link the tags with corresponding resources, ...therefore leading to a static user profile in the recommendation. In this article, we have proposed a new social tag expansion model (STEM) to generate a dynamic user profile to improve the recommendation performance. Instead of simply including most relevant tags, the new model focuses on the completeness of a user profile through expanding tags by exploiting their relations and includes a sufficient set of tags to alleviate the tag sparsity problem. The novel STEM-based TRS contains three operations: (1) Tag cloud generation discovers potentially relevant tags in an application domain; (2) Tag expansion finds a sufficient set of tags upon original tags; and (3) User profile refactoring builds a dynamic user profile and determines the weights of the extended tags in the profile. We analysed the STEM property in terms of recommendation accuracy and demonstrated its performance through extensive experiments over multiple datasets. The analysis and experimental results showed that the new STEM technique was able to correctly find a sufficient set of tags and to improve the recommendation accuracy by solving the tag sparsity problem. At this point, this technique has consistently outperformed state-of-art tag-aware recommendation methods in these extensive experiments.
In recent decades, recommendation systems (RS) have played a pivotal role in societal life, closely intertwined with people's everyday activities. However, traditional recommendation systems still ...require thorough consideration of comprehensive user profiles as they have struggled to provide more personalized and accurate recommendation services. This paper delves into the analysis and enrichment of user profiles, utilizing this foundation to tailor recommendations for individuals across domains such as movies, TV shows, and books. The paper constructs a chart comprising 246 types of user profile attributes, primarily covering dimensions like gender, age, occupation, and religious beliefs, among 16 other dimensions. This chart integrates approximately 1.2 million data points, encompassing information relevant to movies, TV shows, and novels. Through training on the dataset, the study has enhanced the model's recommendation effectiveness. Post-training, the recommendation accuracy surpasses that of pre-training based on proposed evaluation metrics. Furthermore, post-manual evaluation, the recommended results are more reasonable and align better with user profiles.
•The study surveyed users and non-users in a city where e-scooters became rapidly a trend.•Shared e-scooters mostly replaced walking and public transport trips.•People travelling with bicycle or ...motorcycle were not attracted by e-scooters novelty.•Males are more likely to be engaged with the new mobility option.•Both users and non-users identified the lack of infrastructure as a critical aspect.
Micromobility and especially e-scooter sharing have recently attracted a lot of attention, due to the rapid spreading of e-scooters in many cities around the world. However, many local authorities have not yet been prepared for efficiently integrating e-scooters in their transport systems and the exact impact of e-scooters is still unclear. It is therefore essential to understand the way e-scooters operate and their users’ profile. To address these questions, a study was designed based on 578 questionnaires (271 by e-scooter users and 307 by non-users) in the city of Thessaloniki, Greece. The analysis utilized a classification tree model for identifying the characteristics of people that are attracted by e-scooters (i.e., used them more than once) and a latent variable logit model for understanding the attributes of the regular e-scooter users. The results show that shared e-scooters mostly replaced walking and public transport trips; therefore, the positive impact of e-scooters on the environment is questioned. Also, the results indicate that people traveling with bicycle or motorcycle were not at all attracted by e-scooters. Moreover, females seem to be less keen on using e-scooters compared to males, while people living downtown are more regular users compared with those living in longer distances from the city center. These findings can aid policymakers in shaping the manner with which e-scooters can be incorporated in their cities.
Electricity bill-sensitive user profiling in the power industry is gradually being recognized as a research hotspot. A multi-layer feature construction method has been proposed, separating the mining ...of textual and numerical information, addressing the insufficient exploration of textual data in existing user profile processing methods. The complexity of electricity user profiles is addressed through the introduction of a two-stage predictive model based on Stacking ensemble learning. In the first stage, user sensitivity is predicted by utilizing the advantages of MLP (Multi-Layer Perceptron), CNN-LSTM (Convolutional Neural Network-Long Short-Term Memory), and XGB (Extreme Gradient Boosting) in global, local, and missing value handling, respectively. In the second stage, electricity-sensitive users are identified by employing RF (Random Forest). The experimental results show that the MLS-SEL user profile model is higher than the models MVEM, SG and SMUPM in terms of both F1 value and accuracy rate. It is implied that users who could be more sensitive to fluctuations in electricity costs have been identified more accurately.
•Multi-Layer Feature Construction:The method isolates textual and numerical data mining, addressing the underexplored textual information in user profiles for a more comprehensive understanding.•Two-Stage Stacking Model:Using Stacking ensemble learning, the model integrates various algorithms (MLP, CNN-LSTM, XGB, RF) effectively, ensuring accurate predictions of user sensitivity in handling global, local, and missing value aspects.•Improved Accuracy:Experimental results demonstrate MLS-SEL’s superior performance over existing models (MVEM, SG, SMUPM) in accurately identifying users sensitive to electricity cost fluctuations, marking a significant advancement.
Use of online social networks (OSNs) undoubtedly brings the world closer. OSNs like Twitter provide a space for expressing one’s opinions in a public platform. This great potential is misused by the ...creation of bot accounts, which spread fake news and manipulate opinions. Hence, distinguishing genuine human accounts from bot accounts has become a pressing issue for researchers. In this paper, we propose a framework based on deep learning to classify Twitter accounts as either ‘human’ or ‘bot.’ We use the information from user profile metadata of the Twitter account like description, follower count and tweet count. We name the framework ‘DeeProBot,’ which stands for Deep Profile-based Bot detection framework. The raw text from the description field of the Twitter account is also considered a feature for training the model by embedding the raw text using pre-trained Global Vectors (GLoVe) for word representation. Using only the user profile-based features considerably reduces the feature engineering overhead compared with that of user timeline-based features like user tweets and retweets. DeeProBot handles mixed types of features including numerical, binary, and text data, making the model hybrid. The network is designed with long short-term memory (LSTM) units and dense layers to accept and process the mixed input types. The proposed model is evaluated on a collection of publicly available labeled datasets. We have designed the model to make it generalizable across different datasets. The model is evaluated using two ways: testing on a hold-out set of the same dataset; and training with one dataset and testing with a different dataset. With these experiments, the proposed model achieved AUC as high as 0.97 with a selected set of features.