The graph-based recommendation systems achieve significant success, yet they are accompanied by malicious attacks. In most scenes, attackers will inject crafted fake profiles into the recommendation ...system to boost the ranking of their target items in the recommendation lists. For an exploration of potential attacks hidden in real life, researchers have proposed various attacks with severe threats. However, current efforts in exploring attack strategies neglect the stealthiness aspect of the attack, i.e., the perturbation of recommendation performance after an attack can be quite noticeable, potentially alerting the defenders. To fill this research gap, this paper introduces a novel attack framework named InfoAtk, designed to conduct attacks while ensuring stealthiness. Specifically, given the dependency of precise recommendation predominantly on representations, the framework employs contrastive learning techniques to align representations before and after the attack, thereby augmenting stealthiness. Additionally, we optimize the representation of target items to outrank the last items in users’ recommendation lists, thereby promoting the visibility of the target item to increase the attack’s effectiveness. Extensive experiments on four public datasets validate the stealthiness and effectiveness of our proposed attack framework.
•We explore the stealthiness of recommender attack to fill this research gap.•We introduce a poisoning attack method based on a bi-level optimization framework.•We leverage contrastive learning to align item embeddings for stealthiness.•We boost attack effectiveness with minimum cost by optimizing target item embedding.•Our experiments show the stealthiness and effectiveness of our attack.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Both reviews and user-item interactions (i.e., rating scores) have been widely adopted for user rating prediction. However, these existing techniques mainly extract the latent representations for ...users and items in an independent and static manner. That is, a single static feature vector is derived to encode user preference without considering the particular characteristics of each candidate item. We argue that this static encoding scheme is incapable of fully capturing users’ preferences, because users usually exhibit different preferences when interacting with different items. In this article, we propose a novel
c
ontext-
a
ware user-item
r
epresentation
l
earning model for rating prediction, named CARL. CARL derives a joint representation for a given user-item pair based on their individual latent features and latent feature interactions. Then, CARL adopts Factorization Machines to further model higher order feature interactions on the basis of the user-item pair for rating prediction. Specifically, two separate learning components are devised in CARL to exploit review data and interaction data, respectively:
review-based feature learning
and
interaction-based feature learning
. In the review-based learning component, with convolution operations and attention mechanism, the pair-based relevant features for the given user-item pair are extracted by jointly considering their corresponding reviews. However, these features are only reivew-driven and may not be comprehensive. Hence, an interaction-based learning component further extracts complementary features from interaction data alone, also on the basis of user-item pairs. The final rating score is then derived with a dynamic linear fusion mechanism. Experiments on seven real-world datasets show that CARL achieves significantly better rating prediction accuracy than existing state-of-the-art alternatives. Also, with the attention mechanism, we show that the pair-based relevant information (i.e., context-aware information) in reviews can be highlighted to interpret the rating prediction for different user-item pairs.
Recommendation systems (RS) have dramatically evolved these past few years, generating more and more accurate results and developing innovative filtering methods. A huge breakthrough was the ...integration of ontologies into their recommendation process. It integrated the domain's knowledge into its reasoning process, thus overcoming the limitations of the conventional RS. The main purpose of this paper is to explore the application of ontology-based RS within critical infrastructure projects implementing the systems engineering or model-based engineering approach.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Explainable recommendation systems (ERSs) have attracted increasing attention from researchers, which generate high-quality recommendations with intuitive explanations to help users make appropriate ...decisions. However, most of the existing ERSs are designed with an offline setting, which can hardly adjust their models using the online feedback instantly for improved performance. To overcome the limitations of ERSs with the offline setting, we propose a novel online setting for ERSs and devise an effective model called O3ERS in this online setting, which can perform online learning with good scalability and rigorous theoretical guides for better online recommendations and online explanations. O3ERS also addresses two challenging problems in real scenarios, namely, the sparsity and delay of online explanations’ feedback as well as the partialness and insufficiency of online recommendations’ feedback. Specifically, O3ERS not only instantly leverages the knowledge learned from the recommendations’ feedback to adjust the sparse and delayed explanations’ feedback for better explanations but also utilizes a novel exploitation–exploration strategy that incorporates the explanations’ feedback to adjust the partial and insufficient recommendations’ feedback for better recommendations. Our theoretical analysis and empirical studies on one simulated and two real-world datasets show that our model outperforms the state-of-the-art models in online scenarios remarkably.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Pairwise preference information, which involves users expressing their preferences by comparing items, plays a crucial role in decision-making and has recently found application in recommendation ...systems. In this study, we introduce GcPp, a clustering algorithm that leverages pairwise preference data to generate recommendations for user groups. Initially, we construct individual graphs for each user based on their pairwise preferences and utilize a graph convolutional network to predict similarities between all pairs of graphs. These predicted similarity scores form the foundation of our research. We then construct a new graph where users are nodes and the edges are weighted according to the predicted similarities. Finally, we perform clustering on the graph’s nodes (users). By evaluating various metrics, we found that employing a similarity metric based on a convolutional neural network (SimGNN) with our proposed ground truth called Top-K yielded the highest accuracy. The proposed approach is specifically designed for group recommendation systems and holds significant potential for group decision-making problems. Code is available at https://github.com/RozaAbolghasemi/Group_Recommendation_Syatem_GcPp_clustering.
•For precise and fair group recommendations, one can use clusters of similar users as groups.•The introduced GcPp is a Graph Clustering method based on Pairwise Preferences data.•User similarity is determined by shared preferences, diverging from conventional feature vectors.•Similarity prediction using both overall user preference (Top-K) and detailed pairwise preferences.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Dynamic recommendation systems aim to achieve real-time updates and dynamic migration of user interests, primarily utilizing user-item interaction sequences with timestamps to capture the dynamic ...changes in user interests and item attributes. Recent research has mainly centered on two aspects. First, it involves modeling the dynamic interaction relationships between users and items using dynamic graphs. Second, it focuses on mining their long-term and short-term interaction patterns. This is achieved through the joint learning of static and dynamic embeddings for both users and items. Although most existing methods have achieved some success in modeling the historical interaction sequences between users and items, there is still room for improvement, particularly in terms of modeling the long-term dependency structures of dynamic interaction histories and extracting the most relevant delayed interaction patterns. To address this issue, we proposed a Dynamic Context-Aware Recommendation System for dynamic recommendation. Specifically, our model is built on a dynamic graph and utilizes the static embeddings of recent user-item interactions as dynamic context. Additionally, we constructed a Gated Multi-Layer Perceptron encoder to capture the long-term dependency structure in the dynamic interaction history and extract high-level features. Then, we introduced an Attention Pooling network to learn similarity scores between high-level features in the user-item dynamic interaction history. By calculating bidirectional attention weights, we extracted the most relevant delayed interaction patterns from the historical sequence to predict the dynamic embeddings of users and items. Additionally, we proposed a loss function called the Pairwise Cosine Similarity loss for dynamic recommendation to jointly optimize the static and dynamic embeddings of two types of nodes. Finally, extensive experiments on two real-world datasets, LastFM, and the Global Terrorism Database showed that our model achieves consistent improvements over state-of-the-art baselines.
Many websites over the Internet are producing a variety of textual data; such as news, research articles, ebooks, personal blogs, and user reviews. In these websites, the textual data is so large ...that the process of finding pertinent information by a user often becomes cumbersome. To overcome this issue, "Text-based Recommendation Systems (RS)" are being developed. They are the systems with the capability to find the relevant information in a minimal time using text as the primary feature. There exist several techniques to build and evaluate such systems. And though a good number of surveys compile the general attributes of recommendation systems, there is still a lack of comprehensive literature review about the text-based recommendation systems. In this paper, we present a review of the latest studies on text-based RS. We have conducted this survey by collecting literature from preeminent digital repositories, that was published during the period 2010-2020. This survey mainly covers the four major aspects of the textual based recommendation systems used in the reviewed literature. The aspects are datasets, feature extraction techniques, computational approaches, and evaluation metrics. As benchmark datasets carry a vital role in any research, publicly available datasets are extensively reviewed in this paper. Moreover, for text-based RS many proprietary datasets are also used, which are not available in the public. But we have consolidated all the attributes of these publically available and proprietary datasets to familiarize these attributes to new researchers. Furthermore, the feature extraction methods from the text are briefed and their usage in the construction of text-based RS are discussed. Later, various computational approaches that use these features are also discussed. To evaluate these systems, some evaluation metrics are adopted. We have presented an overview of these evaluation metrics and diagramed them according to their popularity. The survey concludes that Word Embedding is the widely used feature selection technique in the latest research. The survey also deduces that hybridization of text features with other features enhance the recommendation accuracy. The study highlights the fact that most of the work is on English textual data, and News recommendation is the most popular domain.
With the developments of e-commerce websites, user textual review has become an important source of information for improving the performance of recommendation systems, as they contain fine-grained ...users’ opinions that generally reflect their preference towards products. However, most of the classical recommender systems (RSs) often ignore such user opinions and therefore fail to precisely capture users’ specific sentiments on products. Although a few of the approaches have attempted to utilize fine-grained users’ opinions for enhancing the accuracy of recommendation systems to some extent, most of these methods basically rely on handcrafted and rule-based approaches that are generally known to be time-consuming and labour-intensive. As such, their application is limited in practice. Thus, to overcome the above problems, this paper proposes a recommendation system that utilizes aspect-based opinion mining (ABOM) based on the deep learning technique to improve the accuracy of the recommendation process. The proposed model consists of two parts: ABOM and rating prediction. In the first part, we use a multichannel deep convolutional neural network (MCNN) to better extract aspects and generate aspect-specific ratings by computing users’ sentiment polarities on various aspects. In the second part, we integrate the aspect-specific ratings into a tensor factorization (TF) machine for the overall rating prediction. Experimental results using various datasets show that our proposed model achieves significant improvements compared with the baseline methods.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Dyslexia is the most widespread specific learning disorder and significantly impair different cognitive domains. This, in turn, negatively affects dyslexic students during their learning path. ...Therefore, specific support must be given to these students. In addition, such a support must be highly personalized, since the problems generated by the disorder can be very different from one to another. In this work, we explored the possibility of using AI to suggest the most suitable supporting tools for dyslexic students, so as to provide a targeted help that can be of real utility. To do this, we relied on recommendation algorithms, which are a branch of machine learning, that aim to detect personal preferences and provide the most suitable suggestions. We hence implemented and trained three collaborative-filtering recommendation models, namely an item-based, a user-based and a weighted-hybrid model, and studied their performance on a large database of 1237 students’ information, collected with a self-evaluating questionnaire regarding all the most used supporting strategies and digital tools. Each recommendation model was tested with three different similarity metrics, namely Pearson correlation, Euclidean distance and Cosine similarity. The obtained results showed that a recommendation system is highly effective in suggesting the optimal help tools/strategies for everyone, with an error less then 12%. As a further evidence of the effectiveness of the implemented system, its precision was 0.85 and its recall was 0.83. The best performing filter was the hybrid one, when Pearson’s correlation is used to measure the distance among users and/or items. In addition, in a final testing performed on 50 students, dyslexic students who used the recommendation algorithm increased their academic scores of almost 1 point in a 1 to 10 scale, showing higher learning performance compared to students who did not use it. This demonstrates that the proposed approach is successful and can be used as a new and effective methodology to support students with dyslexia.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Over the years, various techniques of generating recommendations have been developed. However, it turns out that when we compare the recommendations generated by different algorithms in the context ...of a particular user, the quality of such recommendations for different techniques may differ. The use of the aggregation techniques, the aim of which is to combine several rankings into one, can be a solution to this problem. In theory it should improve the quality of the recommendations. Additionally, in order to personalize the recommendations better, a metaheuristic algorithm, which, by assigning different weights to each feature, tries to represent the preference of the active user, was used. This paper also presents a suggestion to include additional rankings generated for other users in the system in the aggregation process. The idea will be supported by research results that clearly show that taking into account rankings of other users can improve the quality of the generated recommendations.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP