Personalized Tag Recommendation Research Articles

A Graph Neural Networks-Based Learning Framework With Hyperbolic Embedding for Personalized Tag Recommendation

A Graph Neural Networks-Based Learning Framework With Hyperbolic Embedding for Personalized Tag Recommendation

Low Dimensional Relevance Coding for Personalized Tag Recommendation in Image Tagging Applications

An approach of image coding for tag recommendation based on feature clustering and weighted coding is presented in this paper. The existing tag recommendation approach develops a decision based on correlation of image features and their tag annotated. The descriptive feature of the image sample defines the content of an image and is correlated with database features for tag recommendation. The feature dimension and its representation have a greater impact on the recommendation performance. The recent method tag recommendation developed CNN based visual features and proposed a tag recommendation based on weight factor. The dimensional feature and the isolated weight allocation limit the performance of presented tag recommendation system. This paper presents a new weight allocation and feature clustering method for tag recommendation. An approach of integral coding for weighted image-tag is presented to improve recommendation accuracy. The proposed recommendation system performance is tested on Flickr dataset for retrieval and recommendation accuracy.

Video topic detection on Micro-Blog using Relational Topic Model

To enhance the performance of the personalized tag recommendation method, a microblog video topic discovery algorithm based on common knowledge atlas analysis was proposed. Firstly, graphical form was used for expressing latent local expression in the microblog video topic and top-k similar user discovery of users represented by user topic distribution. Then, the frequency of all the tags occurring in these users was calculated and the tags most relevant with users were recommended. Next, to mine potential topic information, enhanced cosine similarity RTM model with penalty term was used for naming the tag of topic for microblog video, which enhanced the impact of united modeling on tag generation for potential topic and might discover the relationship between global tab and topic. At last, the real experiment result showed that the recommended method was superior to typical tag recommendation algorithms of several selected microblog video topics. Meanwhile, the validity of the algorithm was verified.

Neural Graph for Personalized Tag Recommendation

Traditional personalized tag recommendation methods cannot guarantee that the coupling relationships hidden in the interactions among entities are effectively encoded in the process of learning the representations of entities, resulting in insufficient expressive capacity for characterizing the preferences or attributes of entities. In this article, we first propose a graph neural networks boosted personalized tag recommendation model, namely NGTR, which integrates the graph neural networks into the pairwise interaction tensor factorization model. Specifically, we exploit the graph neural networks to capture the coupling relationships and integrate the coupling relationships into the learning of representations of entities by transmitting and assembling the representations of neighbors along the interaction graphs. In addition, we also propose a light graph neural networks boosted personalized tag recommendation model, namely LNGTR. Different from NGTR, our proposed LNGTR model removes feature transformation and nonlinear activation components as well as adopts the weighted sum of the embeddings learned at all layers as the final embedding. Experimental results on real world datasets show that our proposed personalized tag recommendation models outperform the traditional tag recommendation methods.

Hierarchical attention model for personalized tag recommendation

AbstractWith the development of Web‐based social networks, many personalized tag recommendation approaches based on multi‐information have been proposed. Due to the differences in users' preferences, different users care about different kinds of information. In the meantime, different elements within each kind of information are differentially informative for user tagging behaviors. In this context, how to effectively integrate different elements and different information separately becomes a key part of tag recommendation. However, the existing methods ignore this key part. In order to address this problem, we propose a deep neural network for tag recommendation. Specifically, we model two important attentive aspects with a hierarchical attention model. For different user‐item pairs, the bottom layered attention network models the influence of different elements on the features representation of the information while the top layered attention network models the attentive scores of different information. To verify the effectiveness of the proposed method, we conduct extensive experiments on two real‐world data sets. The results show that using attention network and different kinds of information can significantly improve the performance of the recommendation model, and verify the effectiveness and superiority of our proposed model.

Adversarial Learning for Personalized Tag Recommendation

We have recently seen great progress in image classification due to the success of deep convolutional neural networks and the availability of large-scale datasets. Most of the existing work focuses on single-label image classification. However, there are usually multiple tags associated with an image. The existing works on multi-label classification are mainly based on lab curated labels. Humans assign tags to their images differently, which is mainly based on their interests and personal tagging behavior. In this paper, we address the problem of personalized tag recommendation and propose an end-to-end deep network which can be trained on large-scale datasets. The user-preference is learned within the network in an unsupervised way where the network performs joint optimization for user-preference and visual encoding. A joint training of user-preference and visual encoding allows the network to efficiently integrate the visual preference with tagging behavior for a better user recommendation. In addition, we propose the use of adversarial learning, which enforces the network to predict tags resembling user-generated tags. We demonstrate the effectiveness of the proposed model on two different large-scale and publicly available datasets, YFCC100 M and NUS-WIDE. The proposed method achieves significantly better performance on both the datasets when compared to the baselines and other state-of-the-art methods. The code is publicly available at https://github.com/vyzuer/ALTReco.

Personalized Tag Recommendation Based on Convolution Feature and Weighted Random Walk

Automatic image semantic annotation is of great importance for image retrieval, therefore, this paper aims to recommend tags for social images according to user preferences. With the rapid development of the image-sharing community, such as Flickr, the image resources of the social network with rich metadata information demonstrate explosive growth. How to provide semantic tagging words (also known as tag recommendation) to social images through image metadata information analysis and mining is still a question, which brings new challenges and opportunities to the semantic understanding of images. Making full use of metadata for semantic analysis of images can help to bridge the semantic gap. Thus, we propose a novel personalized tag recommendation algorithm based on the convolution feature and weighted random walk. Particularly, for a given target image, we select its visual neighbors and determine the weight of each neighbor by mining the influence of user group metadata in Flickr on image correlation, and combining group information and visual features extracted by Convolutional Neural Network (CNN). Afterwards, the weighted random walk algorithm is implemented on the neighbor-tag bipartite graph. Experimental results show that tags recommended by our proposed method can accurately describe the semantic information of images and satisfy the personalized requirements of users.

PERSONALIZED GEO-TAG RECOMMENDATION FOR COMMUNITY CONTRIBUTED IMAGES

Tagging is popularized by many social sharing websites, which allows us to add the description to object. Using tags users can organize their data so that it will be helpful for searching and browsing. Geotagging of a photo is the process in which a photo is marked with the geographical identification of the place it was taken. Geotagging can benefit users, to discover an Extensive Variation of exact Location related information. In personalized tag recommendation, tags that are relevant to the user's query are retrieved based upon the user's interest. The introduction of the Hypergraph learning is to find joint relevance between the visual and textual domains. Given a photo with Geolocation and without tags, System uses nearest neighbour search to obtain some user- predilected tags and geo-location predilected tags individually. It discovers the semantically and visually related images, and explores the idea of annotation-by-search to recommend tags for the untagged photo. In conclusion, the tags are recommended to the user.

Personalized Tag Recommendation through Nonlinear Tensor Factorization Using Gaussian Kernel

Personalized tag recommendation systems recommend a list of tags to a user when he is about to annotate an item. It exploits the individual preference and the characteristic of the items. Tensor factorization tech- niques have been applied to many applications, such as tag recommendation. Models based on Tucker Decomposition can achieve good performance but require a lot of computation power. On the other hand, mod- els based on Canonical Decomposition can run in linear time and are more feasible for online recommendation. In this paper, we propose a novel method for personalized tag recommendation, which can be considered as a nonlinear extension of Canonical Decomposition. Different from linear tensor factorization, we exploit Gaussian radial basis function to increase the model’s capacity. The experimental results show that our proposed method outperforms the state-of-the-art methods for tag recommendation on real datasets and perform well even with a small number of features, which verifies that our models can make better use of features.

Personalized Tag Recommendation Based on Transfer Matrix and Collaborative Filtering

In social tagging systems, users are allowed to label resources with tags, and thus the system builds a personalized tag vocabulary for every user based on their distinct preferences. In order to make the best of the personalized characteristic of users’ tagging behavior, firstly the transfer matrix is used in this paper, and the tag distributions of query resources are mapped to users’ query before the recommendation. Meanwhile, we find that only considering the user’s preference model, the method cannot recommend new tags for users. So we utilize the thought of collaborative filtering, and produce the recommend tags based on the query user and his/her nearest neighbors' preference models. The experiments conducted on the Delicious corpus show that our method combining transfer matrix with collaborative filtering produces better recommendation results.

Ranking on heterogeneous manifolds for tag recommendation in social tagging services

Abstract Nowadays, most social Websites allow users to annotate resources (such as Web pages and images) with keywords, i.e. tags. Collaborative tagging data reflects the semantic perception of users, thus providing valuable information for the related recommendation problems, e.g. tag recommendation, resource recommendation. In this paper, we tackle the problem of personalized tag recommendation in social tagging services by generalizing the traditional manifold ranking idea. Specifically, we model the complex relationships in tagging data as a heterogeneous graph and propose a novel ranking algorithmic framework for heterogeneous manifolds, named GRoMO (Graph-based Ranking of Multi-type interrelated Objects). In our system both the resource to be tagged (accounting for relevance) and the user׳s historical tags (accounting for personalization) are treated as query inputs. Then tags are ranked according to the output of GRoMO and the top tags are recommended to that user. We also explore adapting GRoMO for resource recommendation. For experiments we crawled a tagging dataset from the well-known tagging service, Del.icio.us. Experimental results indicate (1) the proposed method is effective and significantly outperforms baseline methods; (2) the iterative form solutions of GRoMO converge very fast and can be used when the dataset is large; (3) GRoMO can also be used for resource recommendation.

Personalized and object-centered tag recommendation methods for Web 2.0 applications

Several Web 2.0 applications allow users to assign keywords (or tags) to provide better organization and description of the shared content. Tag recommendation methods may assist users in this task, improving the quality of the available information and, thus, the effectiveness of various tag-based information retrieval services, such as searching, content recommendation and classification. This work addresses the tag recommendation problem from two perspectives. The first perspective, centered at the object, aims at suggesting relevant tags to a target object, jointly exploiting the following three dimensions: (i) tag co-occurrences, (ii) terms extracted from multiple textual features (e.g., title, description), and (iii) various metrics to estimate tag relevance. The second perspective, centered at both object and user, aims at performing personalized tag recommendation to a target object-user pair, exploiting, in addition to the three aforementioned dimensions, a metric that captures user interests.In particular, we propose new heuristic methods that extend state-of-the-art strategies by including new metrics that estimate how accurately a candidate tag describes the target object. We also exploit three learning-to-rank (L2R) based techniques, namely, RankSVM, Genetic Programming (GP) and Random Forest (RF), for generating ranking functions that exploit multiple metrics as attributes to estimate the relevance of a tag to a given object or object-user pair. We evaluate the proposed methods using data from four popular Web 2.0 applications, namely, Bibsonomy, LastFM, YouTube and YahooVideo. Our new heuristics for object-centered tag recommendation provide improvements in precision over the best state-of-the-art alternative of 12% on average (up to 20% in any single dataset), while our new heuristics for personalized tag recommendation produce average gains in precision of 121% over the baseline. Similar performance gains are also achieved in terms of other metrics, notably recall, Normalized Discounted Cumulative Gain (NDCG) and Mean-Reciprocal Rank (MRR). Further improvements, for both object-centered (up to 23% in precision) and personalized tag recommendation (up to 13% in precision), can also be achieved with our new L2R-based strategies, which are flexible and can be easily extended to exploit other aspects of the tag recommendation problem. Finally, we also quantify the benefits of personalized tag recommendation to provide better descriptions of the target object when compared to object-centered recommendation by focusing only on the relevance of the suggested tags to the object. We find that our best personalized method outperforms the best object-centered strategy, with average gains in precision of 10%.

Personalized Geo-Specific Tag Recommendation for Photos on Social Websites

Social tagging becomes increasingly important to organize and search large-scale community-contributed photos on social websites. To facilitate generating high-quality social tags, tag recommendation by automatically assigning relevant tags to photos draws particular research interest. In this paper, we focus on the personalized tag recommendation task and try to identify user-preferred, geo-location-specific as well as semantically relevant tags for a photo by leveraging rich contexts of the freely available community-contributed photos. For users and geo-locations, we assume they have different preferred tags assigned to a photo, and propose a subspace learning method to individually uncover the both types of preferences. The goal of our work is to learn a unified subspace shared by the visual and textual domains to make visual features and textual information of photos comparable. Considering the visual feature is a lower level representation on semantics than the textual information, we adopt a progressive learning strategy by additionally introducing an intermediate subspace for the visual domain, and expect it to have consistent local structure with the textual space. Accordingly, the unified subspace is mapped from the intermediate subspace and the textual space respectively. We formulate the above learning problems into a united form, and present an iterative optimization with its convergence proof. Given an untagged photo with its geo-location to a user, the user-preferred and the geo-location-specific tags are found by the nearest neighbor search in the corresponding unified spaces. Then we combine the obtained tags and the visual appearance of the photo to discover the semantically and visually related photos, among which the most frequent tags are used as the recommended tags. Experiments on a large-scale data set collected from Flickr verify the effectivity of the proposed solution.

Personalized tag recommendation based on generalized rules

Tag recommendation is focused on recommending useful tags to a user who is annotating a Web resource. A relevant research issue is the recommendation of additional tags to partially annotated resources, which may be based on either personalized or collective knowledge. However, since the annotation process is usually not driven by any controlled vocabulary, the collections of user-specific and collective annotations are often very sparse. Indeed, the discovery of the most significant associations among tags becomes a challenging task. This article presents a novel personalized tag recommendation system that discovers and exploits generalized association rules, that is, tag correlations holding at different abstraction levels, to identify additional pertinent tags to suggest. The use of generalized rules relevantly improves the effectiveness of traditional rule-based systems in coping with sparse tag collections, because: (i) correlations hidden at the level of individual tags may be anyhow figured out at higher abstraction levels and (ii) low-level tag associations discovered from collective data may be exploited to specialize high-level associations discovered in the user-specific context. The effectiveness of the proposed system has been validated against other personalized approaches on real-life and benchmark collections retrieved from the popular photo-sharing system Flickr.

Personalized Tag Recommendation Using Social Influence

Tag recommendation encourages users to add more tags in bridging the semantic gap between human concept and the features of media object, which provides a feasible solution for content-based multimedia information retrieval. In this paper, we study personalized tag recommendation in a popular online photo sharing site — Flickr. Social relationship information of users is collected to generate an online social network. From the perspective of network topology, we propose node topological potential to characterize user’s social influence. With this metric, we distinguish different social relations between users and find out those who really have influence on the target users. Tag recommendations are based on tagging history and the latent personalized preference learned from those who have most influence in user’s social network. We evaluate our method on large scale real-world data. The experimental results demonstrate that our method can outperform the non-personalized global co-occurrence method and other two state-of-the-art personalized approaches using social networks. We also analyze the further usage of our approach for the cold-start problem of tag recommendation.

Personalized topic-based tag recommendation

More and more content on the Web is generated by users. To organize this information and make it accessible via current search technology, tagging systems have gained tremendous popularity. Especially for multimedia content they allow to annotate resources with keywords (tags) which opens the door for classic text-based information retrieval. To support the user in choosing the right keywords, tag recommendation algorithms have emerged. In this setting, not only the content is decisive for recommending relevant tags but also the user's preferences. In this paper we introduce an approach to personalized tag recommendation that combines a probabilistic model of tags from the resource with tags from the user. As models we investigate simple language models as well as Latent Dirichlet Allocation. Extensive experiments on a real world dataset crawled from a big tagging system show that personalization improves tag recommendation, and our approach significantly outperforms state-of-the-art approaches.

PUT-Tag: personalized user-centric tag recommendation for social bookmarking systems

Social bookmarking systems have been growing significantly in recent years. They allow users to bookmark URLs using their own keywords, known as tags. Tags can be used later for searching and categorizing bookmarks. With the growth of social bookmarking systems, the need to automatically recommend tags increases. Among the most popular approaches for tag recommendation is collaborative filtering. In this work, we address two main limitations of collaborative filtering, the first-time seen bookmarks that have not been tagged before and the cold-start users that have no sufficient history to use for recommendation. The focus of this work is to make social personalized tag recommendation for social bookmarking systems based on finding similar users and similar bookmarks. We proposed a new personalized tag recommendation system, PUT-Tag, that uses tag, user and content similarity in recommending tags. The experimental evaluation illustrated that the PUT-Tag algorithm outperforms benchmark approaches. Moreover, it achieves a similar performance when considering first time URLs for both active and cold-start users.

Improving Graph-based Approaches for Personalized Tag Recommendation

Social tagging applications allow users to annotate online resources, resulting in a complex network of interrelated users, resources and tags often called a Folksonomy. A folk- sonomy is often represented as a hyper-graph in which each hyper-edge connects a user, resource and tag. This tripartite hyper-graph is often used by data mining applications to provide services for the user such as tag recommenders. This paper provides an overview on the state of the art of graph-based tag recommendation from a critical perspective. In addition, we suggest improving the existing graph-based tag recommendation techniques by introducing a new model of the folksonomy as a directed graph. I. INTRODUCTION Collaborative tagging systems such as Delicious 1 , lastFm 2 , and Bibsonomy 3 have emerged as powerful applications for Internet users. Tagging systems support users with several benefits. First they allow users to organize their own data with a level of freedom not possible in traditional taxonomic filing systems. Secondly they provide users with the means to openly share this information among friends and colleagues. Thirdly they also allow anyone to utilize the collective knowledge of others for discovering new topics, resources or perhaps even new friends. While social tagging systems have many benefits, they also present several challenges. Most tagging applications permit unsupervised tagging; users are free to use any tag they wish to describe a resource. This unsupervised tagging can result in tag redundancy - in which several tags have the same meaning - or tag ambiguity - in which a single tag has many different meanings. Such inconsistencies can confound users as they attempt to utilize the folksonomy. It can be difficult for users to traverse the sheer volume of data. Moreover, noise in the data can impede the users experience. Data mining applications such as tag recommenders make it easier for the user to navigate the system. Tag recommendation, the suggestion of tags during the annotation process reduces the user effort. By reducing the effort users are encouraged to tag more frequently, apply more tags to an individual resource, reuse common tags, and perhaps use tags the user had not previously considered. Moreover, user error is reduced by eliminating redundant tags caused by capitalization inconsistencies, punctuation errors, 1http://delicious.com/ 2 http://www.last.fm/ 3 www.bibsonomy.org/ misspellings and other discrepancies. The tag recommender can further promote a core tag vocabulary steering the user toward adopting certain tags while not imposing any strict rules. The tag recommender may even avoid ambiguous tags in favor of tags that offer greater information value. This may aid other users when navigating through the folksonomy to find interesting resources related to a tag which is more often used by other users. In order to develop a recommender applications in a social tagging system the first step is to create a model of the folksonomy that takes into account the information flow between users, resources and tags. In this paper we present a critical view on the existing graph-based tag recommendation approaches specifically on one of the most popular techniques, called FolkRank. In addition, we propose a weighted directed graph which models the informational channels of a folksonomy. We then apply PageRank to this model for tag recommendation. Our claim for a directed graph to model the folksonomy is based on the observation that the user navigation from one object (user, resource, or tag) to another object is not symmetric and by considering different weights on the edges of each direction we can better model the navigating from one node to the other.

Exploring Social Relations for Personalized Tag Recommendation in Social Tagging Systems

With the emergence of Web 2.0, social tagging systems become highly popular in recent years and thus form the so-called folksonomies. Personalized tag recommendation in social tagging systems is to provide a user with a ranked list of tags for a specific resource that best serves the user's needs. Many existing tag recommendation approaches assume that users are independent and identically distributed. This assumption ignores the social relations between users, which are increasingly popular nowadays. In this paper, we investigate the role of social relations in the task of tag recommendation and propose a personalized collaborative filtering algorithm. In addition to the social annotations made by collaborative users, we inject the social relations between users and the content similarities between resources into a graph representation of folksonomies. To fully explore the structure of this graph, instead of computing similarities between objects using feature vectors, we exploit the method of random-walk computation of similarities, which furthermore enable us to model a user's tag preferences with the similarities between the user and all the tags. We combine both the collaborative information and the tag preferences to recommend personalized tags to users. We conduct experiments on a dataset collected from a real-world system. The results of comparative experiments show that the proposed algorithm outperforms state-of-the-art tag recommendation algorithms in terms of prediction quality measured by precision, recall and NDCG.