Dario De Nart

A Personalized Concept-driven Recommender System for Scientific Libraries☆

Abstract Recommender Systems can greatly enhance the exploitation of large digital libraries; however, in order to achieve good accuracy with collaborative recommenders some domain assumptions must be met, such as having a large number of users sharing similar interests over time. Such assumptions may not hold in digital libraries, where users are structured in relatively small groups of experts whose interests may change in unpredictable ways: this is the case of scientific and technical documents archives. Moreover, when recommending documents, users often expect insights on the recommended content as well as a detailed explanation of why the system has selected it, which cannot be provided by collaborative techniques. In this paper we consider the domain of scientific publications repositories and propose a content-based recommender based upon a graph representation of concepts built up by linked keyphrases. This recommender is coupled with a keyphrase extraction system able to generate meaningful metadata for the documents, which are the basis for providing helpful and explainable recommendations.

A New Multi-lingual Knowledge-base Approach to Keyphrase Extraction for the Italian Language

Associating meaningful keyphrases to text documents and Web pages is an activity that can significantly increase the accuracy of Information Retrieval, Personalization and Recommender systems, but the growing amount of text data available is too large for an extensive manual annotation. On the other hand, automatic keyphrase generation can significantly support this activity. This task is already performed with satisfactory results by several systems proposed in the literature, however, most of them focuses solely on the English language which represents approximately more than 50% of Web contents. Only few other languages have been investigated and Italian, despite being the ninth most used language on the Web, is not among them. In order to overcome this shortage, we propose a novel multi-language, unsupervised, knowledge-based approach towards keyphrase generation. To support our claims, we developed DIKpE-G, a prototype system which integrates several kinds of knowledge for selecting and evaluating meaningful keyphrases, ranging from linguistic to statistical, meta/structural, social, and ontological knowledge. DIKpE-G performs well over English and

Personalized Access to Scientific Publications: from Recommendation to Explanation

Several recommender systems have been proposed in the literature for adaptively suggesting useful references to researchers with different interests. However, in order to access the knowledge contained in the recommended papers, the users need to read the publications for identifying the potentially interesting concepts. In this work we propose to overcome this limitation by utilizing a more semantic approach where concepts are extracted from the papers for generating and explaining the recommendations. By showing the concepts used to find the recommended articles, users can have a preliminary idea about the filtered publications, can understand the reasons why the papers were suggested and they can also provide new feedback about the relevance of the concepts utilized for generating the recommendations.

Digital Libraries on the Move

Smart Data is a central element for the Publishing Industry. A review of the rich data published by Elsevier via 9 Research platforms will be presented. Particular emphasis will be devoted to our investments in Knowledge graphs, Information Extraction, and Entity annotation. After this initial introduction, we will focus our attention on three particular applications built on top of our rich data. Authors’ disambiguation is an open research problem where the goal is to match different identities attributed to the same Author during his/her life. Article fingerprinting is a rich set of information extraction techniques used for classifying articles and for building analytical tools leveraged by research institutions. News Trend detection is another rich set of matching tools used for tracking how institutions and researchers are mentioned by public and social media.

A Content-Based Approach to Social Network Analysis: A Case Study on Research Communities

Several works in literature investigated the activities of research communities using big data analysis, but the large majority of them focuses on papers and co-authorship relations, ignoring that most of the scientific literature available is already clustered into journals and conferences with a well defined domain of interest. We are interested in bringing out underlying implicit relationships among such containers and more specifically we are focusing on conferences and workshop proceedings available in open access and we exploit a semantic/conceptual analysis of the full free text content of each paper. We claim that such content-based analysis may lead us to a better understanding of the research communities’ activities and their emerging trends. In this work we present a novel method for research communities activity analysis, based on the combination of the results of a Social Network Analysis phase and a Content-Based one. The major innovative contribution of this work is the usage of knowledge-based techniques to meaningfully extract from each of the considered papers the main topics discussed by its authors.

Modelling the User Modelling Community (and Other Communities as Well)

Discovering and modelling research communities’ activities is a task that can lead to a more effective scientific process and support the development of new technologies. Journals and conferences already offer an implicit clusterization of researchers and research topics, and social analysis techniques based on co-authorship relations can highlight hidden relationships among researchers, however, little work has been done on the actual content of publications. We claim that a content-based analysis on the full text of accepted papers may lead to a better modelling and understanding of communities’ activities and their emerging trends. In this work we present an extensive case study of research community modelling based upon the analysis of over 450 events and 7000 papers.

RES: A Personalized Filtering Tool for CiteSeerX Queries Based on Keyphrase Extraction

Finding satisfactory scientific literature is still a very time-consuming task. In the last decade several tools have been proposed to approach this task, however only few of them actually analyse the whole document in order to select and present it to the user and even less tools offer any kind of explanation of why a given item was retrieved/recommended. The main goal of this demonstration is to present the RES system, a tool intended to overcome the limitations of traditional recommender and personalized information retrieval systems by exploiting a more semantic approach where concepts are extracted from the papers in order to generate and then explain the recommendation. RES acts like a personalized interface for the well-known CiteSeerX system, filtering and presenting query results accordingly to individual user’s interests.

Fast, Accurate, Multilingual Semantic Relatedness Measurement Using Wikipedia Links

In this chapter we present a fast, accurate, and elegant metric to assess semantic relatedness among entities included in an hypertextual corpus building an novel language independent Vector Space Model. Such a technique is based upon the Jaccard similarity coefficient, approximated with the MinHash technique to generate a constant-size vector fingerprint for each entity in the considered corpus. This strategy allows evaluation of pairwise semantic relatedness in constant time, no matter how many entities are included in the data and how dense the internal link structure is. Being semantic relatedness a subtle and somewhat subjective matter, we evaluated our approach by running user tests on a crowdsourcing platform. To achieve a better evaluation we considered two collaboratively built corpora: the English Wikipedia and the Italian Wikipedia, which differ significantly in size, topology, and user base. The evaluation suggests that the proposed technique is able to generate satisfactory results, outperforming commercial baseline systems regardless of the employed data and the cultural differences of the considered test users.

Stratifying Semantic Data for Citation and Trust: An Introduction to RDFDF

In this paper we analyse the functional requirements of linked data citation and identify a minimal set of operations and primitives needed to realise such task. Citing linked data implies solving a series of data provenance issues and finding a way to identify data subsets. Those two tasks can be handled defining a simple type system inside data and verifying it with a type checker, which is significantly less complex than interpreting reified RDF statements and can be implemented in a non data invasive way. Finally we suggest that data citation should be handled outside of the data, and propose a simple language to describe RDF documents where separation between data and metainformation is explicitly specified.

Leveraging Arabic morphology and syntax for achieving better keyphrase extraction

Arabic is one of the fastest growing languages on the Web, with an increasing amount of user generated content being published by both native and non-native speakers all over the world. Despite the great linguistic differences between Arabic and western languages such as English, most Arabic keyphrase extraction systems rely on approaches designed for western languages, thus ignoring its rich morphology and syntax. In this paper we present a new approach leveraging the Arabic morphology and syntax to generate a restricted set of meaningful candidates among which keyphrases are selected. Though employing a small set of well-known features to select the final keyphrases, our system consistently outperforms the well-known and established systems.