User Embeddings Research Articles

Meta-GRS: A Graph Neural Network for Cross-Domain Recommender System via Meta-Learning

Despite the fact that Recommender Systems have been researched and developed for quite a while, they still hold some certain challenges, two of which are Cold Start and Data Sparsity. Being introduced as a savior, the Cross-domain Recommender system (CDR) owns the capacity to transfer knowledge across domains which makes it become the practical solution for the mentioned issues. In CDR approaches, the family of graph-based solutions is very effective, which builds graphs to illustrate the relationship between users, items, and other factors and learn their representations through graph representation learning. However, most graph-based approaches focus on extracting either domain-specific or domain-shared features and do not have the mechanism to prevent the transfer of private features, which can degrade the quality of vector representations. Moreover, the knowledge transfer process built on overlapping users makes the model biased toward these users, thus downgrading the performance on cold-start users. This paper proposes a meta-GRS framework that uses Graph Neural Network with Meta-Learning and Adversarial Learning for cross-domain recommendation. In meta-GRS, the representative user and item embeddings are improved thanks to the features extracted by the private and cross-domain graphs. Domain-shared features are learned under adversarial learning such that the domain discriminator is unable to determine whether the domain they came from can ensure the positive transfer. To optimize the model performance effectively, we use a Dynamic Weight Averaging algorithm to learn loss weights automatically. The model's parameters are optimized under the optimization-based meta-learning method provides our model the capability of generalization to the new users. Experiments on practical datasets illustrate that the meta-GRS leads the chart in the comparison of other state-of-the-art baselines in recommendation accuracy.

Self-Supervised Learning for Multimedia Recommendation

Learning representations for multimedia content is critical for multimedia recommendation. Current representation learning methods roughly fall into two groups: (1) using the historical interactions to create ID embeddings of users and items, and (2) treating multi-modal data as the side information of items to enrich their ID embeddings. Each user-item interaction offers the supervisory signal to optimize the representation learning by the traditional supervised learning paradigm. Due to the overlook of the multi-modal patterns (<inline-formula><tex-math notation="LaTeX">$e.g.$</tex-math></inline-formula>, co-occurrence of visual, acoustic, textual features in micro-videos a user saw before, and her behavioral features) hidden in the data, these methods are insufficient to create powerful representations and obtain satisfactory recommendation accuracy. To capture multi-modal patterns in the data itself, we go beyond the supervised learning paradigm, and incorporate the idea of self-supervised learning (SSL) into multimedia recommendation. Specifically, SSL consists of two components: (1) data augmentation upon multi-modal contents, where we design three operators &#x2014; feature dropout (FD), feature masking (FM), feature fine and coarse spaces (FAC) &#x2014; to generate multiple views of individual items; and (2) contrastive learning, which differentiates the views of an item from the others&#x2019; to distill additional supervisory signals. Clearly, SSL enables us to explore and exhibit the underlying relations among modalities, thereby resulting in powerful representations. We denote the generic framework by <i>Self-supervised Learning-guided Multimedia Recommendation</i> (SLMRec). Extensive experiments are performed on three real-world datasets, showing that SLMRec achieves significant improvements over several state-of-the-art baselines like LightGCN [1], MMGCN [2]. Further analysis shows how SSL affects recommendation performance.

UPRec: User-aware Pre-training for sequential Recommendation

Recent years witness the success of pre-trained models to alleviate the data sparsity problem in recommender systems. However, existing pre-trained models for recommendation mainly focus on leveraging universal sequence patterns from user behavior sequences and item information, whereas ignore heterogeneous user information to capture personalized interests, which has been shown to contribute to the personalized recommendation. In this paper, we propose a simple yet effective model, called User-aware Pre-training for Recommendation (UPRec), which could flexibly encode heterogeneous user information into the sequential modeling of user behaviors. Specifically, UPRec first encodes the sequential behavior to generate user embeddings, and then jointly optimizes the model with the sequential objective and user-aware objective constructed from the user attributes and structured social graphs. Comprehensive experimental results on two real-world large-scale recommendation datasets demonstrate that UPRec can effectively enrich the user representations with user attributes and social relations and thus provide more appropriate recommendations for users.

Adversarial Auto-encoder Domain Adaptation for Cold-start Recommendation with Positive and Negative Hypergraphs

This article presents a novel model named Adversarial Auto-encoder Domain Adaptation to handle the recommendation problem under cold-start settings. Specifically, we divide the hypergraph into two hypergraphs, i.e., a positive hypergraph and a negative one. Below, we adopt the cold-start user recommendation for illustration. After achieving positive and negative hypergraphs, we apply hypergraph auto-encoders to them to obtain positive and negative embeddings of warm users and items. Additionally, we employ a multi-layer perceptron to get warm and cold-start user embeddings called regular embeddings. Subsequently, for warm users, we assign positive and negative pseudo-labels to their positive and negative embeddings, respectively, and treat their positive and regular embeddings as the source and target domain data, respectively. Then, we develop a matching discriminator to jointly minimize the classification loss of the positive and negative warm user embeddings and the distribution gap between the positive and regular warm user embeddings. In this way, warm users’ positive and regular embeddings are connected. Since the positive hypergraph maintains the relations between positive warm user and item embeddings, and the regular warm and cold-start user embeddings follow a similar distribution, the regular cold-start user embedding and positive item embedding are bridged to discover their relationship. The proposed model can be easily extended to handle the cold-start item recommendation by changing inputs. We perform extensive experiments on real-world datasets for both cold-start user and cold-start item recommendations. Promising results in terms of precision, recall, normalized discounted cumulative gain, and hit rate verify the effectiveness of the proposed method.

A hierarchical fused fuzzy deep neural network with heterogeneous network embedding for recommendation

The integration of deep learning (DL) and fuzzy learning (FL) is considered a recently emerging and promising research direction in data embedding. The integrated fuzzy neural learning paradigm within deep learning-based recommendation helped improving the performance of both latent feature representation learning and multiple recommendation problem fine-tuning. In general, feature representation learning is considered an important component of modern deep-learning based recommendation systems (RS). However, many well-known deep learning-based recommendation techniques encounter major challenges, which are mainly related to data uncertainty and the presence of noise in the obtained user and item embeddings. Moreover, most of the deep embedding-based RSs have still relied much on the local proximity relationships. These proximity features are obtained from the direct user-item interactions in order to leverage the recommendation outputs. This limitation has led to several difficulties in effectively extracting the rich latent structural features of users and items. In addition, in previous meta-path-based embedding techniques for the HIN-based recommendation approach, the integration between multi-type path-based representation learning for recommendation often encounters challenges concerning feature uncertainty extraction. To overcome the aforementioned problems, in this paper we propose a novel fuzzy-driven HIN embedding model for recommendation, called FuzzyRec. The proposed FuzzyRec has an integrated hierarchical fused neural fuzzy and deep network-based embedding architecture. It supports effective learning of the representations of users and items, as well as reducing feature ambiguity and noise. Extensive experiments demonstrate the effectiveness of our proposed method and its advantages compared with state-of-the-art baselines for recommendation systems.

Adversarial Learning for Cross Domain Recommendations

Existing cross domain recommender systems typically assume homogeneous user preferences across multiple domains to capture similarities of user-item interactions and to provide cross domain recommendations accordingly. Meanwhile, the heterogeneity of user behaviors is usually not well studied and captured during the recommendation process, where users might have vastly different interests in different domains. In addition, previous models focus primarily on recommendation tasks between domain pairs, and cannot be naturally extended to serve for multiple domain recommendation applications. To address these challenges, we propose to utilize the idea of adversarial learning to intelligently incorporate global user preferences and domain-specific user preferences for providing satisfying cross domain recommendations. In particular, our proposed Adversarial Cross Domain Recommendation (ACDR) model first obtains the latent representations of global user preferences from their explicit feature information, and then transforms them into domain-specific user embeddings, where we take into account user behaviors and their heterogeneous preferences among different domains. By doing so, we address the differences among user representations in the domain-specific latent space while also preserving global user preferences, as we effectively segment the distributions of domain-specific user embeddings in the shared latent space. The convergence of our proposed model is theoretically guaranteed. The proposed ACDR model leads to significant and consistent improvements in cross domain recommendation performance over the state-of-the-art baseline models, which we demonstrate through extensive experiments on three real-world datasets. In addition, we show that the improvements are greater on those datasets that are smaller and more sparse, on those users that have fewer interaction records in the dataset, and when user interactions from more product domains are included in the cross domain recommendation model.

Social Recommendation Based on Multi-Auxiliary Information Constrastive Learning

Social recommendation can effectively alleviate the problems of data sparseness and the cold start of recommendation systems, attracting widespread attention from researchers and industry. Current social recommendation models use social relations to alleviate the problem of data sparsity and improve recommendation performance. Although self-supervised learning based on user–item interaction can enhance the performance of such models, multi-auxiliary information is neglected in the learning process. Therefore, we propose a model based on self-supervision and multi-auxiliary information using multi-auxiliary information, such as user social relationships and item association relationships, to make recommendations. Specifically, the user social relationship and item association relationship are combined to form a multi-auxiliary information graph. The user–item interaction relationship is also integrated into the same heterogeneous graph so that multiple pieces of information can be spread in the same graph. In addition, we utilize the graph convolution method to learn user and item embeddings, whereby the user embeddings reflect both user–item interaction and user social relationships, and the item embeddings reflect user–item interaction and item association relationships. We also design multi-view self-supervising auxiliary tasks based on the constructed multi-auxiliary views. Signals generated by self-supervised auxiliary tasks can alleviate the problem of data sparsity, further improving user/item embedding quality and recommendation performance. Extensive experiments on two public datasets verify the superiority of the proposed model.

EAGCN: An Efficient Adaptive Graph Convolutional Network for Item Recommendation in Social Internet of Things

In the era of Internet of Things (IoT), intelligent recommendation is playing an important role in our daily life. How to provide personalized information to users is the core concern of Internet content service providers. To improve the recommendation quality, it is a hot topic to go beyond merely user–item interaction records and take social relations into account in IoT. Recently, emerged graph neural networks (GNNs) shine a light on simulating the recursive social diffusion process, to refine user embedding learning. Nevertheless, two key issues have not been well studied in previous studies: 1) they usually model user preference and social influence within a same semantic space and fail to simultaneously inject high-order connectivity information reflected in both user–item interaction graph and user–user social graph and 2) they typically rely on negative sampling to optimize a recommendation model, which makes them highly sensitive to the design of the sampler and hardly makes full use of GPU’s computing ability. In light of this, we propose a novel framework for item recommendation, namely, an efficient adaptive graph convolutional network (EAGCN). Specifically, we introduce a space-adaptive graph convolutional module, which could jointly explore the propagation process of user interest and social influence. Furthermore, a user-specific gating mechanism is designed to aggregate user representations from both spaces. To make EAGCN practical in social IoT, we devise a fast nonsampling leaner to optimize EAGCN’s parameters with better leveraging matrix computing of GPU. Extensive experiments under four scenarios show that our solution consistently and significantly outperforms strong baseline methods in both model effectiveness and training efficiency.

Efficient complementary graph convolutional network without negative sampling for item recommendation

Learning vector representations (a.k.a., embeddings) of users and items lies at the heart of building a modern recommender system. Typically, graph neural networks (GNN) have been a prevalent way to learn user and item embeddings with implicit feedback. Nevertheless, since item popularity in many recommendation scenarios follows a long-tail distribution, we argue that recent GNN-based recommenders are not sufficient to yield satisfactory embeddings, especially for tail items. More importantly, most of GNN-based methods depend on negative sampling in model optimization, which makes them inefficient in the GPU era and highly sensitive to the design of negative sampler. In light of these limitations, we propose a novel recommendation method named ECGN, short for efficient complementary graph convolutional network. Specifically, by means of the complementary relationships amongst items, we introduce a complementary-aware graph convolution module, which better alleviates the long-tail problem. By regarding user behaviors and item relationships as two bipartite graphs, such module could explicitly explore the propagation process of user interest and complementary influence. Furthermore, an item-specific attention mechanism is designed to fuse item representations from different bipartite graphs. To make our solution attractive in large-scale industrial scenarios, we devise an efficient non-sampling learning paradigm to optimize ECGN’s parameters. Experiments on six real-world datasets demonstrate that our method consistently and significantly outperforms several state-of-the-art methods in model effectiveness and training efficiency. Our implementations and datasets are available at https://github.com/wubinzzu/ECGN.

Federated Social Recommendation with Graph Neural Network

Recommender systems have become prosperous nowadays, designed to predict users’ potential interests in items by learning embeddings. Recent developments of the Graph Neural Networks (GNNs) also provide recommender systems (RSs) with powerful backbones to learn embeddings from a user-item graph. However, only leveraging the user-item interactions suffers from the cold-start issue due to the difficulty in data collection. Hence, current endeavors propose fusing social information with user-item interactions to alleviate it, which is the social recommendation problem. Existing work employs GNNs to aggregate both social links and user-item interactions simultaneously. However, they all require centralized storage of the social links and item interactions of users, which leads to privacy concerns. Additionally, according to strict privacy protection under General Data Protection Regulation, centralized data storage may not be feasible in the future, urging a decentralized framework of social recommendation.As a result, we design a federated learning recommender system for the social recommendation task, which is rather challenging because of its heterogeneity, personalization, and privacy protection requirements. To this end, we devise a novel frameworkFedratedSocial recommendation withGraph neural network (FeSoG). Firstly,FeSoGadopts relational attention and aggregation to handle heterogeneity. Secondly,FeSoGinfers user embeddings using local data to retain personalization. Last but not least, the proposed model employs pseudo-labeling techniques with item sampling to protect the privacy and enhance training. Extensive experiments on three real-world datasets justify the effectiveness ofFeSoGin completing social recommendation and privacy protection. We are the first work proposing a federated learning framework for social recommendation to the best of our knowledge.

Graph Transformer Collaborative Filtering Method for Multi-Behavior Recommendations

Graph convolutional networks are widely used in recommendation tasks owing to their ability to learn user and item embeddings using collaborative signals from high-order neighborhoods. Most of the graph convolutional recommendation tasks in existing studies have specialized in modeling a single type of user–item interaction preference. Meanwhile, graph-convolution-network-based recommendation models are prone to over-smoothing problems when stacking increased numbers of layers. Therefore, in this study we propose a multi-behavior recommendation method based on graph transformer collaborative filtering. This method utilizes an unsupervised subgraph generation model that divides users with similar preferences and their interaction items into subgraphs. Furthermore, it fuses multi-headed attention layers with temporal coding strategies based on the user–item interaction graphs in the subgraphs such that the learned embeddings can reflect multiple user–item relationships and the potential for dynamic interactions. Finally, multi-behavior recommendation is performed by uniting multi-layer embedding representations. The experimental results on two real-world datasets show that the proposed method performs better than previously developed systems.

Incorporating multi‐interest into recommendation with graph convolution networks

In recent years, the appearance of graph convolutional networks (GCNs) provides a new idea for graph structure data processing. Because of that, they can learn excellent user and item embedding by using cooperative signals of high-order neighbors, and the GCNs technique shows great potential in the recommendation. The common problem with the bulk of GCN-based models is that it appears the situation of performance degradation during the stacking of network layers. The recently proposed IMP-GCN alleviates this problem to some extent. It aims to avoid the influence of downside information from high-order propagation on embedding learning. However, we consider that it ignores the multi-interest factor, in which users may have different interests. In this paper, we present a multi-interest GCN(MI-GCN) model for a recommendation, and it conducts high-order graph convolution operations in three sets of subgraphs. Users with similar interests and the corresponding interaction items belong to the identical subgraph. As for the formation of the subgraph, we adopt two varied clustering methods and the user feature to form a subgraph generation mechanism. This mechanism can generate three groups of differential subgraphs to divide users into multi-interest groups and make subgraph division more reasonable. We carry out massive experiments on three real-world datasets, demonstrating the effectiveness of our model. Experimental results confirm that our presented MI-GCN outperforms the state-of-the-art GCN-based recommendation models.

Abnormal User Detection via Multiview Graph Clustering in the Mobile e-Commerce Network

In recent years, Internet of Things has not only promoted the continuous development of e-commerce transaction but also brought loop-hole to the fraud gangs who always utilize mobile devices to commit fraud crimes. For example, fraud gangs are usually organized to purchase commodities at low prices in e-commerce promotions. They benefit from the price spread by reselling commodities at high prices. In the past few years, the transaction fraud caused serious financial losses to merchants in e-commerce platform. To detect the fraudulent user and behavior effectively, a multiview graph clustering-based abnormal detection model is developed in this paper. In the proposed model, two fraudulent behavior patterns are proposed by abstracting the e-commerce network as a heterogeneous information graph. On this basis, two user-similarity graphs are reorganized from the heterogeneous graph with the help of different metapaths. Subsequently, in order to capture the corresponding fraudulent behavior patterns, the above two graphs are encoded into user embeddings and assigned to specific clusters in respective views. Finally, the consensus detection result is produced by fusing the complementary information of different views in a joint multiview learning framework. As we know, our work is the first one that uses multiview graph clustering in e-commerce fraud detection, which will provide a new research perspective for fraud detection in e-commerce platform. Extensive experiments are conducted on real and semisynthetic datasets, and the results demonstrate the effectiveness and superiority of the proposed model.

Who Will Travel With Me? Personalized Ranking Using Attributed Network Embedding for Pooling

In ride matching, the search results can be personalized for a particular driver. Given a query with trip plans, it is advantageous to rank potential riders in terms of who are most appealing to the driver for increasing occupancy rates. While personalized ranking approaches such as collaborative filtering and factorization are available, they are not suitable for pooling because candidate riders are associated with different preferences, and their travel is sparsely distributed with a long tail of users for a few popular destinations. The user embedding method is a good candidate in terms of alleviating data sparsity, but it has issues such as difficulty encoding user preferences from rich information. In this study, we explore user embedding techniques for the purposes of short-term personalized rider ranking, where the aim is to present to drivers a set of potential riders who share similar itineraries with them and can be picked up on their current route. Considering trip requests, along with the preferences issued in advance, this study uses attribute representations to rank the riders based on the higher-order similarities in the participants’ itineraries in a three-step manner: (i) start with a distributed representation of the riders’ preference regarding the cost of extra distance, (ii) generate user embeddings in a heterogeneous network with the meeting points and associated waiting times, and (iii) match and rank riders for drivers depending on an attribute fusion operation by adopting a personal route and schedule. Our proposed method performs well in an offline estimation on a huge dataset from DiDi in Chengdu, China. Experimental results indicate that with the learned embeddings, we can obtain statistically significant advancements (e.g., 4.6–29.5% increase in mean reciprocal rank (MRR); 2.8–17.4% in normalized discounted cumulative gain (nDCG)) over current methods for pooling ranking. Furthermore, we implement the proposed method on our simulated pooling system. These results validate that personalized ranking can undoubtedly boost the number of trips served, and reduce the total trip distance and waiting time.

Privacy-Aware Factorization-Based Hybrid Recommendation Method for Healthcare Services

With the advancements of the Health 2.0 technology, large-scale healthcare services are available online. Recommender systems for healthcare services have emerged for decision assistance. Most existing collaborative recommendation algorithms only mine global interactions while failing to capture the local different information of users or items. Besides, privacy concern is another significant problem to be considered in recommender systems for healthcare services. In this article, a privacy-aware factorization-based hybrid method is proposed for healthcare service recommendations. For better modeling of user preferences and service features, multiview embeddings of users and healthcare services are learned. Besides, we address the privacy problem by integrating local differential privacy and locality-sensitive hashing techniques into the recommendation model for privacy-aware neighbor searching. The final prediction is made based on a stochastic gradient descent learning-based hybrid collaborative model. Experiments demonstrate the effectiveness of the proposed method in both recommendation performance and privacy concerns.

Two-Layer Matrix Factorization and Multi-Layer Perceptron for Online Service Recommendation

Service recommendation is key to improving users’ online experience. The development of the Internet has accelerated the creation of many services, and whether users can obtain good experiences among the massive number of services mainly depends on the quality of service recommendation. It is commonly believed that deep learning has excellent nonlinear fitting ability in capturing the complex interactions between users and items. The advantage in learning intricacy relationships enables deep learning to become an important technology for present service recommendation. Recently, it is noticed that linear models can perform almost as well as the state-of-the-art deep learning models, suggesting that capturing linear relationships between users and items is also very important for recommender systems. Therefore, numerous deep learning systems combined with linear models have been proposed. However, existing models are incapable of considering the size of the embedding. When the embedding dimension is too large, it leads to overfitting and thus influences the model’s ability to capture linear relationships. In this paper, a neural network based on two-layer matrix factorization and multi-layer perceptron—Two-layer Matrix factorization and Multi-layer perceptron Neural Network (TMMNN)—is proposed. To solve the problem of overfitting caused by an oversized embedding dimension, multi-size embedding technology has been integrated into the model. Matrix factorization and the multi-layer perceptron are placed in the upper and lower layers respectively, and they both receive embedding vectors dynamically adjusted for dimensions. In the upper layer, the matrix factorization is responsible for receiving the embedding of users and items, capturing linear relationships, and then yielding the generated new vectors as input to the multi-layer perceptron in the lower layer. Compared to other previously proposed models, the experimental results on the standard datasets MovieLens 20M and MovieLens Latest show that the TMMNN model is evidently better in terms of prediction accuracy.

Session-Based Graph Attention POI Recommendation Network

Point-of-interest (POI) recommendation which aims at predicting the locations that users may be interested in has attracted wide attentions due to the development of Internet of Things and location-based services. Although collaborative filtering based methods and deep neural network have gain great success in POI recommendation, data sparsity and cold start problem still exist. To this end, this paper proposes session-based graph attention network (SGANet for short) for POI recommendation by making use of regional information. Specifically, we first extract users’ features from the regional history check-in data in session windows. Then, we use graph attention network to learn users’ preferences for both POI and regional POI, respectively. We learn the long-term and short-term preferences of users by fusing the user embedding and POI ancillary information through gate recurrent unit. Finally, we conduct experiments on two real world location-based social network datasets Foursquare and Gowalla to verify the effectiveness of the proposed recommendation model and the experiments results show that SGANet outperformed the compared baseline models in terms of recommendation accuracy, especially in sparse data and cold start scenario.

FedCTR: Federated Native Ad CTR Prediction with Cross-platform User Behavior Data

Native ad is a popular type of online advertisement that has similar forms with the native content displayed on websites. Native ad click-through rate (CTR) prediction is useful for improving user experience and platform revenue. However, it is challenging due to the lack of explicit user intent, and user behaviors on the platform with native ads may be insufficient to infer users’ interest in ads. Fortunately, user behaviors exist on many online platforms that can provide complementary information for user-interest mining. Thus, leveraging multi-platform user behaviors is useful for native ad CTR prediction. However, user behaviors are highly privacy-sensitive, and the behavior data on different platforms cannot be directly aggregated due to user privacy concerns and data protection regulations. Existing CTR prediction methods usually require centralized storage of user behavior data for user modeling, which cannot be directly applied to the CTR prediction task with multi-platform user behaviors. In this article, we propose a federated native ad CTR prediction method named FedCTR, which can learn user-interest representations from cross-platform user behaviors in a privacy-preserving way. On each platform a local user model learns user embeddings from the local user behaviors on that platform. The local user embeddings from different platforms are uploaded to a server for aggregation, and the aggregated ones are sent to the ad platform for CTR prediction. Besides, we apply local differential privacy and differential privacy to the local and aggregated user embeddings, respectively, for better privacy protection. Moreover, we propose a federated framework for collaborative model training with distributed models and user behaviors. Extensive experiments on real-world dataset show that FedCTR can effectively leverage multi-platform user behaviors for native ad CTR prediction in a privacy-preserving manner.

Disentangling Multi-Facet Social Relations for Recommendation

Social networks have proven to be effective for high-quality item recommendation. Most social recommenders, however, are insufficient to capture the user preferences over items, as they largely neglect the multi-facet social relations latent in the social network, such as classmates, colleagues, and families. We, therefore, propose a novel disentangled social recommendation (DSR) framework to exploit the multifacet social relations for enhanced item recommendation. Specifically, DSR explicitly disentangles the social relations into multiple facets, and encodes the social influence under each facet into disentangled user embeddings in the social network. The multiple user embeddings are then aggregated via a facet-level attention mechanism, which distinguishes the effective facets for better inferring user interests over items. Extensive experiments show the superiority of DSR against the state-of-the-art methods and its potential in alleviating the data sparsity issue.

Twitter User Representation Using Weakly Supervised Graph Embedding

Social media platforms provide convenient means for users to participate in multiple online activities on various contents and create fast widespread interactions. However, this rapidly growing access has also increased the diverse information, and characterizing user types to understand people’s lifestyle decisions shared in social media is challenging. In this paper, we propose a weakly supervised graph embedding based framework for understanding user types. We evaluate the user embedding learned using weak supervision over well-being related tweets from Twitter, focusing on 'Yoga’, 'Keto diet’. Experiments on real-world datasets demonstrate that the proposed framework outperforms the baselines for detecting user types. Finally, we illustrate data analysis on different types of users (e.g., practitioner vs. promotional) from our dataset. While we focus on lifestyle-related tweets (i.e., yoga, keto), our method for constructing user representation readily generalizes to other domains.