Despite substantial advancements in various fields of AI, computational research in career and job domains has been significantly hindered by a critical lack of accessible datasets. This limitation is mainly due to the proprietary nature of job platforms, which restrict the sharing of job-domain datasets with the research community. The scarcity is particularly pronounced for career trajectory and resume datasets, severely constraining academic researchers in developing and evaluating new models. In this paper, we address the crucial issue of resume dataset unavailability in the job domain, identified through our comprehensive comparison of existing job-domain machine learning studies. To the best of our knowledge, we introduce OpenResume, the first publicly available, anonymized, and structured resume dataset, specifically designed for job-domain downstream tasks. This dataset aims to catalyze advancements in AI and foster new markets for machine learning and data science within career trajectory modeling. OpenResume is comprehensively processed from real-world resume data. We anonymize and substitute personal identifiers and company names, normalize job titles into ESCO-based ones (i.e., one of the most common occupation taxonomies), and employ differential privacy techniques on temporal features to ensure open accessibility and privacy protection. Additionally, we augment OpenResume with a synthetically generated resume dataset derived from the post-processed real-world data, extending its diversity and utility. To demonstrate that OpenResume retains challenges and properties similar to real-world job datasets, we benchmark OpenResume on state-of-the-art job-domain prediction models across four prevalent downstream tasks: (1) next job title prediction, (2) next company prediction, (3) turnover prediction, and (4) link prediction. Our experimental results show that these job-domain models perform comparably on OpenResume and the original data across all tasks, demonstrating OpenResume as a valuable career trajectory dataset for both academic research and practical applications. We also indicate the OpenResume applicability for the other eight downstream tasks. Our datasets are available at: https://tinyurl.com/OpenResumeData.

In online job marketplaces, it is important to establish a well-defined job title taxonomy for various downstream tasks (e.g., job recommendation, users’ career analysis, and turnover prediction). Job Title Normalization (JTN) is such a cleaning step to classify user-created non-standard job titles into normalized ones. However, solving the JTN problem is non-trivial with challenges: (1) semantic similarity of different job titles, (2) non-normalized user-created job titles, and (3) large-scale and long-tailed job titles in real-world applications. To this end, we propose a novel solution, named JAMES, that constructs three unique embeddings (i.e., graph, contextuat, and syntactic) of a target job title to effectively capture its various traits. We further propose a multi-aspect co-attention mechanism to attentively combine these embeddings, and employ neural logical reasoning representations to collaboratively estimate similarities between messy job titles and normalized job titles in a reasoning space. To evaluate JAMES, we conduct comprehensive experiments against ten competing models on a large-scale real-world dataset with over 350,000 job titles. Our experimental results show that JAMES significantly outperforms the best baseline by 10.06% in Precision@10 and by 17.52% in NDCG@10, respectively. To further facilitate the acquisition of normalized job titles for job-domain applications, our JAMES API is available at: https://tinyurl.con JAMES-job-title-mapping.

Even though users interacted diversely on items (e.g., click, add-to-cart, and buy), traditional recommendations were mostly built using only the user-item interaction data on the target behavior (e.g., buy), making them suffer from the severe data sparsity issue. To alleviate the problem, recent works on multi-behavior recommendation incorporated multiple types of user-item interactions such as click, add-to-cart, and buy. However, the latest approaches are still limited by overlooking early-stage interactions, and have limited expressiveness of Euclidean geometry. To overcome these issues, in this paper, we propose a Multi-behavior Hyperbolic Graph Recommender (MB-HGR) with two novel aspects. First, it uses multiple heterogeneous graphs to learn multiple user behavior types, where each heterogeneous graph represents a user-item interaction type. This will help not only alleviate the serious data sparsity problem, but also allow the model to explicitly weight different behavior types and prevent information loss. Second, it leverages the expressiveness of the hyperbolic geometry over Euclidean geometry, where exponential growth of distances in the hyperbolic geometry matches the exponential growth of nodes in the hierarchical structures and learns better users/items representations. Experimental results on two public benchmark datasets show that on average our proposed model achieves a significant improvement of 28.32% at Recall@10 and 30.14% at NDCG@10 over the best baseline.

Quaternion space has brought several benefits over the traditional Euclidean space: Quaternions (i) consist of a real and three imaginary components, encouraging richer representations; (ii) utilize Hamilton product which better encodes the inter-latent interactions across multiple Quaternion components; and (iii) result in a model with smaller degrees of freedom and less prone to overfitting. Unfortunately, most of the current recommender systems rely on real-valued representations in Euclidean space to model either user's long-term or short-term interests. In this paper, we fully utilize Quaternion space to model both user's long-term and short-term preferences. We first propose a QUaternion-based self-Attentive Long term user Encoding (QUALE) to study the user's long-term intents. Then, we propose a QUaternion-based self-Attentive Short term user Encoding (QUASE) to learn the user's short-term interests. To enhance our models' capability, we propose to fuse QUALE and QUASE into one model, namely QUALSE, by using a Quaternion-based gating mechanism. We further develop Quaternion-based Adversarial learning along with the Bayesian Personalized Ranking (QABPR) to improve our model's robustness. Extensive experiments on six real-world datasets show that our fused QUALSE model outperformed 11 state-of-the-art baselines, improving 8.43% at [email protected] and 10.27% at [email protected] on average compared with the best baseline.

In this paper, we aim to solve the automatic playlist continuation (APC) problem by modeling complex interactions among users, playlists, and songs using only their interaction data. Prior methods mainly rely on dot product to account for similarities, which is not ideal as dot product is not metric learning, so it does not convey the important inequality property. Based on this observation, we propose three novel deep learning approaches that utilize Mahalanobis distance. Our first approach uses user-playlist-song interactions, and combines Mahalanobis distance scores between (i) a target user and a target song, and (ii) between a target playlist and the target song to account for both the user's preference and the playlist's theme. Our second approach measures song-song similarities by considering Mahalanobis distance scores between the target song and each member song (i.e., existing song) in the target playlist. The contribution of each distance score is measured by our proposed memory metric-based attention mechanism. In the third approach, we fuse the two previous models into a unified model to further enhance their performance. In addition, we adopt and customize Adversarial Personalized Ranking (APR) for our three approaches to further improve their robustness and predictive capabilities. Through extensive experiments, we show that our proposed models outperform eight state-of-the-art models in two large-scale real-world datasets.

Personalized recommendation algorithms learn a user's preference for an item by measuring a distance/similarity between them. However, some of the existing recommendation models (e.g., matrix factorization) assume a linear relationship between the user and item. This approach limits the capacity of recommender systems, since the interactions between users and items in real-world applications are much more complex than the linear relationship. To overcome this limitation, in this paper, we design and propose a deep learning framework called Signed Distance-based Deep Memory Recommender, which captures non-linear relationships between users and items explicitly and implicitly, and work well in both general recommendation task and shopping basket-based recommendation task. Through an extensive empirical study on six real-world datasets in the two recommendation tasks, our proposed approach achieved significant improvement over ten state-of-the-art recommendation models.

Following recent successes in exploiting both latent factor and word embedding models in recommendation, we propose a novel Regularized Multi-Embedding (RME) based recommendation model that simultaneously encapsulates the following ideas via decomposition: (1) which items a user likes, (2) which two users co-like the same items, (3) which two items users often co-liked, and (4) which two items users often co-disliked. In experimental validation, the RME outperforms competing state-of-the-art models in both explicit and implicit feedback datasets, significantly improving [email protected] by 5.9~7.0%, [email protected] by 4.3~5.6%, and [email protected] by 7.9~8.9%. In addition, under the cold-start scenario for users with the lowest number of interactions, against the competing models, the RME outperforms [email protected] by 20.2% and 29.4% in MovieLens-10M and MovieLens-20M datasets, respectively. Our datasets and source code are available at: https://github.com/thanhdtran/RME.git.

In Crowdfunding platforms, people turn their prototype ideas into real products by raising money from the crowd, or invest in someone else's projects. In reward-based crowdfunding platforms such as Kickstarter and Indiegogo, selecting accurate reward delivery duration becomes crucial for creators, backers, and platform providers to keep the trust between the creators and the backers, and the trust between the platform providers and users. According to Kickstarter, 35% backers did not receive rewards on time. Unfortunately, little is known about on-time and late reward delivery projects, and there is no prior work to estimate reward delivery duration. To fill the gap, in this paper, we (i) extract novel features that reveal latent difficulty levels of project rewards; (ii) build predictive models to identify whether a creator will deliver all rewards in a project on time or not; and (iii) build a regression model to estimate accurate reward delivery duration (i.e., how long it will take to produce and deliver all the rewards). Experimental results show that our models achieve good performance -- 82.5% accuracy, 78.1 RMSE, and 0.108 NRMSE at the first 5% of the longest reward delivery duration.

Retweeting/sharing action has enabled information to be cascaded to distant nodes on social network. Unfortunately, malicious users as a group have taken advantage of the retweeting function with coordinated behavior to falsely distort the volume of specific keywords, topics or URLs for promotional purposes (e.g., spreading fake news, and increasing public visibility of products or services). Unfortunately, little is known about their retweeting behavior as a group and how to detect them based on group-based signals. To fill the gap, in this paper, we (i) propose Attractor+ algorithm to extract retweeter groups, members of each of which have similar retweeting behavior; (ii) analyze underlying characteristics of malicious and legitimate retweeter groups; (iii) propose group-based features to catch synchronized and coordinated behavior; and build a predictor to classify if a group is malicious. Experimental results show that our proposed method outperformed existing approaches.

Detecting groups of users, who have similar opinions, interests, or social behavior, has become an important task for many applications. A recent study showed that dynamic distance based Attractor, a community detection algorithm, outperformed other community detection algorithms such as Spectral clustering, Louvain and Infomap, achieving higher Normalized Mutual Information (NMI) and Adjusted Rand Index (ARI). However, Attractor often takes long time to detect communities, requiring many iterations. To overcome the drawback and handle large-scale graphs, in this paper we propose MRAttractor, an advanced version of Attractor to be runnable on a MapReduce framework. In particular, we (i) apply a sliding window technique to reduce the running time, keeping the same community detection quality; (ii) design and implement the Attractor algorithm for a MapReduce framework; and (iii) evaluate MRAttractor's performance on synthetic and real-world datasets. Experimental results show that our algorithm significantly reduced running time and was able to handle large-scale graphs.

In severe outbreaks such as Ebola, bird flu and SARS, people share news, and their thoughts and responses regarding the outbreaks on social media. Understanding how people perceive the severe outbreaks, what their responses are, and what factors affect these responses become important. In this paper, we conduct a comprehensive study of understanding and mining the spread of Ebola-related information on social media. In particular, we (i) conduct a large-scale data-driven analysis of geotagged social media messages to understand citizen reactions regarding Ebola; (ii) build information propagation models which measure locality of information; and (iii) analyze spatial, temporal and social properties of Ebola-related information. Our work provides new insights into Ebola outbreak by understanding citizen reactions and topic-based information propagation, as well as providing a foundation for analysis and response of future public health crises.

As the commercial implications of Likes in online social networks multiply, the number of fake Likes also increase rapidly. To maintain a healthy ecosystem, however, it is critically important to prevent and detect such fake Likes. Toward this goal, in this paper, we investigate the problem of detecting the so-called "fake likers" who frequently make fake Likes for illegitimate reasons. To uncover fake Likes in online social networks, we: (1) first collect a substantial number of profiles of both fake and legitimate Likers using linkage and honeypot approaches, (2) analyze the characteristics of both types of Likers, (3) identify effective features exploiting the learned characteristics and apply them in supervised learning models, and (4) thoroughly evaluate their performances against three baseline methods and under two attack models. Our experimental results show that our proposed methods with effective features significantly outperformed baseline methods, with accuracy = 0.871, false positive rate = 0.1, and false negative rate = 0.14.