An adaptive hybrid movie recommender based on semantic data
4
Citation
2
Reference
20
Related Paper
Citation Trend
Abstract:
Recommender systems assist users in finding relevant entities according to their individual preferences. The entities' properties along with their relationships must be considered in order to articulate good recommendations. In this paper, we present an approach for developing an adaptive hybrid recommender system with semantic data. Such data is represented as large graph of nodes (semantic entities) and edges (semantic relations) filled with contents collected from Linked-Open-Data sources. The system implements different algorithms to generate recommendations supporting users in finding relevant, but potentially unknown movies. The system provides users with explicit explanations helping them to understand why a movie is relevant. Users may refine requests according to their individual preferences. The system considers run-time complexity to guarantee a short request response time for individually adapted requests.Keywords:
Linked Data
Representation
Factor (programming language)
Cite
Citations (5)
Personalized information retrieval and recommendation systems have been proposed to deliver the right information to users with different interests. However, most of previous systems are using keyword frequencies as the main factor for personalization, and as a result, they could not analyze semantic relations between words. Also, previous methods often fail to provide the documents that are related semantically with the query words. To solve these problems, we propose a recommendation system which provides relevant documents to users by identifying semantic relations between an ontology that semantically represents the documents crawled by a Web robot and user behavior history. Recommendation is mainly based on content-based similarity, semantic similarity, and preference weights.
Similarity (geometry)
Cite
Citations (14)
Factor (programming language)
Cite
Citations (47)
Social tagging has revolutionized the social and personal experience of users across numerous web platforms by enabling the organizing, managing, sharing and searching of web data. The extensive amount of information generated by tagging systems can be utilized for recommendation purposes. However, the unregulated creation of social tags by users can produce a great deal of noise and the tags can be unreliable; thus, exploiting them for recommendation is a nontrivial task. In this study, a new recommender system is proposed based on the similarities between user and item profiles. The approach applied is to generate user and item profiles by discovering tag patterns that are frequently generated by users. These tag patterns are categorized into irrelevant patterns and relevant patterns which represent diverse user preferences in terms of likes and dislikes. Furthermore, presented here is a method for translating these tag-based profiles into semantic profiles by determining the underlying meaning(s) of the tags, and mapping them to semantic entities belonging to external knowledge bases. To alleviate the cold start and overspecialization problems, semantic profiles are enriched in two phases: (a) using a semantic spreading mechanism and then (b) inheriting the preferences of similar users. Experiment indicates that this approach not only provides a better representation of user interests, but also achieves a better recommendation result when compared with existing methods. The performance of the proposed recommendation method is investigated in the face of the cold start problem, the results of which confirm that it can indeed remedy the problem for early adopters, hence improving overall recommendation quality.
Folksonomy
Profiling (computer programming)
Cold start (automotive)
Cite
Citations (22)
This paper presents LinkedVis, an interactive visual recommender system that combines social and semantic knowledge to produce career recommendations based on the LinkedIn API. A collaborative (social) approach is employed to identify professionals with similar career paths and produce personalized recommendations of both companies and roles. To unify semantically identical but lexically distinct entities and arrive at better user models, we employ lightweight natural language processing and entity resolution using semantic information from a variety of end-points on the web. Elements from the underlying recommendation algorithm are exposed through an interactive interface that allows users to manipulate different aspects of the algorithm and the data it operates on, allowing users to explore a variety of "what-if" scenarios around their current profile. We evaluate LinkedVis through leave-one-out accuracy and diversity experiments on a data corpus collected from 47 users and their LinkedIn connections, as well as through a supervised study of 27 users exploring their own profile and recommendations interactively. Results show that our approach outperforms a benchmark recommendation algorithm without semantic resolution in terms of accuracy and diversity, and that the ability to tweak recommendations interactively by adjusting profile item and social connection weights further improves predictive accuracy. Questionnaires on the user experience with the explanatory and interactive aspects of the application reveal very high user acceptance and satisfaction.
Benchmark (surveying)
Cite
Citations (33)
Conversational recommender systems (CRS) aim to recommend high-quality items to users through interactive conversations. Although several efforts have been made for CRS, two major issues still remain to be solved. First, the conversation data itself lacks of sufficient contextual information for accurately understanding users' preference. Second, there is a semantic gap between natural language expression and item-level user preference.
Semantic gap
Knowledge graph
Cite
Citations (245)
Basic content personalization consists in matching up the attributes of a user profile, in which preferences and interests are stored, with the attributes of a content object. The Web 2.0 (r)evolution and the advent of user generated content have changed the game for personalization, since the role of people has evolved from passive consumers of information to that of active contributors. One of the forms of user generated content that has drawn more attention from the research community is folksonomy, a taxonomy generated by users who collaboratively annotate and categorize resources of interests with freely chosen keywords called tags.
Folksonomy
User-Generated Content
Content (measure theory)
User profile
Cite
Citations (159)
Recent advances in graph and network embeddings have been utilized for the purpose of providing recommendations. Hybrid recommender systems have shown the efficacy of using side information associated with entities. In this work we show how domain specific knowledge can be used to define meta paths within these heterogeneous domains and how these path constrained random walks can be used to embed user preferences in heterogeneous domains. The semantic embeddings generated from heterogeneous knowledge sources combined with user preferences can be used to refine a user's information needs. This representation modeling of users, entities and their associated properties opens up new modalities of interactions for the users to gravitate towards their requirements. In this work we propose the use of semantic embeddings for two kinds of interactive recommendation modalities: 1) exemplar based recommendations 2) "less like this/ more like this" style recommendations. In our opinion providing these modalities would boost the expressive power of exploratory search and recommender systems.
Modalities
Representation
Expressive power
Cite
Citations (4)
We discuss some methods for constructing recommender systems. An important feature of the methods studied here is that we assume the availability of a description, representation, of me objects being considered for recommendation. The approaches studied here differ from collaborative filtering in that we only use preferences information from the individual for whom we are providing the recommendation and make no use the preferences of other collaborators. We provide a detailed discussion of the construction of me representation schema used. We consider two sources of information about the users preferences. The first are direct statements about the type of objects the user likes. The second source of information comes from ratings of objects which the user has experienced.
Schema (genetic algorithms)
Representation
Feature (linguistics)
Cite
Citations (4)
Information Overload
Digital content
Content (measure theory)
Cite
Citations (6)