Flavius Frasincar

Survey on Aspect-Level Sentiment Analysis

The field of sentiment analysis, in which sentiment is gathered, analyzed, and aggregated from text, has seen a lot of attention in the last few years. The corresponding growth of the field has resulted in the emergence of various subareas, each addressing a different level of analysis or research question. This survey focuses on aspect-level sentiment analysis, where the goal is to find and aggregate sentiment on entities mentioned within documents or aspects of them. An in-depth overview of the current state-of-the-art is given, showing the tremendous progress that has already been made in finding both the target, which can be an entity as such, or some aspect of it, and the corresponding sentiment. Aspect-level sentiment analysis yields very fine-grained sentiment information which can be useful for applications in various domains. Current solutions are categorized based on whether they provide a method for aspect detection, sentiment analysis, or both. Furthermore, a breakdown based on the type of algorithm used is provided. For each discussed study, the reported performance is included. To facilitate the quantitative evaluation of the various proposed methods, a call is made for the standardization of the evaluation methodology that includes the use of shared data sets. Semanticallyrich concept-centric aspect-level sentiment analysis is discussed and identified as one of the most promising future research direction.

Exploiting emoticons in sentiment analysis

As people increasingly use emoticons in text in order to express, stress, or disambiguate their sentiment, it is crucial for automated sentiment analysis tools to correctly account for such graphical cues for sentiment. We analyze how emoticons typically convey sentiment and demonstrate how we can exploit this by using a novel, manually created emoticon sentiment lexicon in order to improve a state-of-the-art lexicon-based sentiment classification method. We evaluate our approach on 2,080 Dutch tweets and forum messages, which all contain emoticons and have been manually annotated for sentiment. On this corpus, paragraph-level accounting for sentiment implied by emoticons significantly improves sentiment classification accuracy. This indicates that whenever emoticons are used, their associated sentiment dominates the sentiment conveyed by textual cues and forms a good proxy for intended sentiment.

Ontology-based news recommendation

Recommending news items is traditionally done by term-based algorithms like TF-IDF. This paper concentrates on the benefits of recommending news items using a domain ontology instead of using a term-based approach. For this purpose, we propose Athena, which is an extension to the existing Hermes framework. Athena employs a user profile to store terms or concepts found in news items browsed by the user. Based on this information, the framework uses a traditional method based on TF-IDF, and several ontology-based methods to recommend new articles to the user. The paper concludes with the evaluation of the different methods, which shows that the new ontology-based method that we propose in this paper performs better (w.r.t. accuracy, precision, and recall) than the traditional method and, with the exception of one measure (recall), also better than the other considered ontology-based approaches.

Hypermedia Presentation Adaptation on the Semantic Web

Web Information Systems (WIS) present up-to-date information on the Web based on data coming from heterogeneous sources. In previous work the Hera methodology was developed to support the design of a WIS. In this paper we target the design of an intelligent WIS. For this reason the Hera methodology is extended with two kinds of hypermedia presentation adaptation: adaptability based on a profile storing device capabilities and user preferences, and adaptivity based on a user model storing the user browsing history. While adaptability is considered to be static, i.e. the presentation is fixed before the browsing starts, adaptivity is dynamic, i.e. the presentation changes while the user is browsing it. The models used in Hera and their adaptation aspects are specified in RDF(S), a flexible Web metadata language designed to support the Semantic Web.

Hera: development of semantic web information systems

As a consequence of the success of the Web, methodologies for information system development need to consider systems that use the Web paradigm. These Web Information Systems (WIS) use Web technologies to retrieve information from the Web and to deliver information in a Web presentation to the users. Hera is a model-driven methodology supporting WIS design, focusing on the processes of integration, data retrieval, and presentation generation. Integration and data retrieval gather from Web sources the data that composes the result of a user query. Presentation generation produces theWeb or hypermedia presentation format for the query result, such that the presentation and specifically its navigation suits the users browser. We show how in Hera all these processes lead to data transformations based on RDF(S) models. Proving the value of RDF(S) for WIS design, we pave the way for the development of Semantic Web Information Systems.

XAL: an algebra for XML query optimization

This paper proposes XAL, an XML ALgebra. Its novelty is based on the simplicity of its data model and its well-defined logical operators, which makes it suitable for composability, optimizability, and semantics definition of a query language for XML data. At the heart of the algebra resides the notion of collection, a concept similar to the mathematicians monad or functional programmers comprehension. The operators are classified in three clusters: extraction operators retrieve the needed information from XML documents, meta-operators control the evaluation of expressions, and construction operators build new XML documents from the extracted data. The resulting algebra has optimization laws similar to the known laws for transforming relational queries. As a consequence, we propose a heuristic optimization algorithm similar to its relational algebra counterpart.

RAL: an algebra for querying RDF

To make the World Wide Web machine-understandable there is a strong demand both for languages describing metadata and for languages querying metadata. The Resource Description Framework (RDF), a language proposed by W3C, can be used for describing metadata about (Web) resources. RDF Schema (RDFS) extends RDF by providing means for creating application specific vocabularies (ontologies). While the two above languages are widely acknowledged as a standard means for describing Web metadata, a standardized language for querying RDF metadata is still an open issue. Research groups coming both from industry and academia are presently involved in proposing several RDF query languages. Due to the lack of an RDF algebra such query languages use APIs to describe their semantics and optimization issues are mostly neglected. This paper proposes RAL (an RDF algebra) as a reference mathematical study for RDF query languages and for performing RDF query optimization. We define the data model, we present the operators to manipulate the data, and we address the application of RAL for query optimization. RAL includes: extraction operators to retrieve the needed resources from the input RDF model, loop operators to support repetition, and construction operators to build the resulting RDF model.

A Semantic Web-Based Approach for Building Personalized News Services

This article proposes Hermes, a Semantic Web-based framework for building personalized news services. It makes use of ontologies for knowledge representation, natural language processing techniques for semantic text analysis, and semantic query languages for specifying wanted information. Hermes is supported by an implementation of the framework, the Hermes News Portal, a tool which allows users to have a personalized online access to news items. The Hermes framework and its associated implementation aim at advancing the state-of-the-art of semantic approaches for personalized news services by employing Semantic Web standards, exploiting domain information, using a word sense disambiguation procedure, and being able to express temporal constraints for the desired news items.

Domain taxonomy learning from text: The subsumption method versus hierarchical clustering

This paper proposes a framework to automatically construct taxonomies from a corpus of text documents. This framework first extracts terms from documents using a part-of-speech parser. These terms are then filtered using domain pertinence, domain consensus, lexical cohesion, and structural relevance. The remaining terms represent concepts in the taxonomy. These concepts are arranged in a hierarchy with either the extended subsumption method that accounts for concept ancestors in determining the parent of a concept or a hierarchical clustering algorithm that uses various text-based window and document scopes for concept co-occurrences. Our evaluation in the field of management and economics indicates that a trade-off between taxonomy quality and depth must be made when choosing one of these methods. The subsumption method is preferable for shallow taxonomies, whereas the hierarchical clustering algorithm is recommended for deep taxonomies.

Faceted product search powered by the Semantic Web

This paper presents a platform for multifaceted product search using Semantic Web technology. Online shops can use a ping service to submit their RDFa annotated Web pages for processing. The platform is able to process these RDFa annotated (X)HTML pages and aggregate product information coming from different Web stores. We propose solutions for the identification of products and the mapping of the categories in this process. Furthermore, when a loose vocabulary such as the Google RDFa vocabulary is used, the platform deals with the issue of heterogeneous information (e.g., currencies, rating scales, etc.).