Content Recommendation through Semantic Annotation of User Reviews and Linked Data

@article{Vagliano2017ContentRT,
  title={Content Recommendation through Semantic Annotation of User Reviews and Linked Data},
  author={Iacopo Vagliano and Diego Monti and Ansgar Scherp and Maurizio Morisio},
  journal={Proceedings of the Knowledge Capture Conference},
  year={2017}
}
Nowadays, most recommender systems exploit user-provided ratings to infer their preferences. However, the growing popularity of social and e-commerce websites has encouraged users to also share comments and opinions through textual reviews. In this paper, we introduce a new recommendation approach which exploits the semantic annotation of user reviews to extract useful and non-trivial information about the items to recommend. It also relies on the knowledge freely available in the Web of Data… 
A Review of Text-Based Recommendation Systems
TLDR
The survey concludes that Word Embedding is the widely used feature selection technique in the latest research and deduces that hybridization of text features with other features enhance the recommendation accuracy.
Recommendations for Item Set Completion: On the Semantics of Item Co-Occurrence With Data Sparsity, Input Size, and Input Modalities
TLDR
It is crucial to consider the semantics of the item co-occurrence for the choice of an appropriate model and carefully decide which metadata to exploit in order to achieve comparable or better performance in the two scenarios of citation and subject label recommendation.
Assisting in semantic enrichment of scholarly resources by connecting neonion and Wikidata
TLDR
It is argued that the re-use of external structured knowledge from Wikidata both fuels an enhanced workflow for assisted subject-matter-sensitive semantic annotation, and allows for the knowledge base to benefit from the structured data generated within neonion in return.
An Exploratory Study on Utilising the Web of Linked Data for Product Data Mining
TLDR
This work focuses on the e-commerce domain and explores how to use structured data in the form of RDF n-quads to create language resources for product data mining tasks and shows word embeddings to be the most reliable and consistent method to improve the accuracy on all tasks.
Mathematics in Wikidata
TLDR
The current state, challenges, and discussions related to integrating Mathematical Entity Linking into Wikidata and Wikipedia are summarized and some data mining methods and applications of the mathematical information are outlined.
A systematic literature review on Wikidata
TLDR
The results collect and summarize existing Wikidata research articles published in the major international journals and conferences, delivering a meticulous summary of all the available empirical research on the topic which is representative of the state of the art at this time, complemented by a discussion of identified gaps and future work.
Training Researchers with the MOVING Platform
TLDR
The MOVING platform is shown how it can support researchers in various tasks, and its main features, such as text and video retrieval and processing, advanced visualizations, and the technologies to assist the learning process are introduced.
Recommending Multimedia Educational Resources on the MOVING Platform
TLDR
This work describes how the recommender is implemented and how it is applied to the MOVING platform to deal with the huge amount of resources stored in the platform, their variety and the increasing number of users.

References

SHOWING 1-10 OF 30 REFERENCES
Challenges in Using Linked Data within a Social Web Recommendation Application to Semantically Annotate and Discover Venues
This paper focuses on a semantically-enhanced Social Web Recommendation application, called Taste It! Try It! It is a mobile restaurants’ review and recommendation application based on a Linked Data
SPrank: Semantic Path-Based Ranking for Top-N Recommendations Using Linked Open Data
TLDR
SPrank is presented, a novel hybrid recommendation algorithm able to compute top-N recommendations exploiting freely available knowledge in the Web of Data and employs DBpedia, a well-known encyclopedic knowledge base in the Linked Open Data cloud, to extract semantic path-based features.
A study of heterogeneity in recommendations for a social music service
TLDR
The obtained results show that, in Last.fm, social tagging and explicit social networking information provide effective and heterogeneous item recommendations, and give first insights on the feasibility of exploiting the above non performance recommendation characteristics by hybrid approaches.
ReDyAl: A Dynamic Recommendation Algorithm based on Linked Data
TLDR
This work describes a new recommendation algorithm based on structured data published on the Web (Linked Data) that exploits existing relationships between resources by dynamically analyzing both the categories to which they belong and their explicit references to other resources.
Informed Recommender: Basing Recommendations on Consumer Product Reviews
TLDR
This work created Informed Recommender to address the problem of using consumer opinion about products, expressed online in free-form text, to generate product recommendations.
A Linked Data Recommender System Using a Neighborhood-Based Graph Kernel
TLDR
This paper presents a CB-RS that leverages LOD and profits from a neighborhood-based graph kernel that is able to compute semantic item similarities by matching their local neighborhood graphs.
Linked Data-Based Concept Recommendation: Comparison of Different Methods in Open Innovation Scenario
TLDR
This work proposes two Linked Data-based concept recommendation methods for topic discovery that exploits only the particularities of Linked data structures and applies a well-known Information Retrieval method, Random Indexing, to the linked data.
Using Linked Data to Build Open, Collaborative Recommender Systems
TLDR
This paper proposes to build open recommender systems which can utilise Linked Data to mitigate the new-user, new-item and sparsity problems of collaborativeRecommender systems.
Semantics-aware Graph-based Recommender Systems Exploiting Linked Open Data
TLDR
A graph-based algorithm leveraging LOD-based features is able to overcome several state of the art baselines, such as collaborative filtering and matrix factorization, thus confirming the effectiveness of the proposed approach.
Recommender Systems and Linked Open Data
TLDR
An overview on recommender systems is presented, how to use Linked Open Data to build a new generation of semantics-aware recommendation engines is sketched and how the data is connected with each other to form the so called LOD cloud is sketches.
...
...