Ionut Cristian Paraschiv

A Paper Recommendation System with ReaderBench: The Graphical Visualization of Semantically Related Papers and Concepts

The task of tagging papers with semantic metadata in order to analyze their relatedness represents a good foundation for a paper recommender system. The analysis from this paper extends from previous research in order to create a graph of papers from a specific domain with the purpose of determining each article’s importance within the considered corpus of papers. Moreover, as non-latent representations are powerful when used in conjunction with latent ones, our system retrieves semantically close words, not present in the paper, in order to improve the retrieval of papers. Our previous analyses used the semantic representation of papers in different semantic models with the purpose of creating visual graphs based on the semantic relatedness links between the abstracts. The current analysis takes a step forward by proposing a model that can suggest which papers are of the highest relevance, share similar concepts, and are semantically related with the initial query. Our study is performed using paper abstracts in the field of information technology extracted from the Web of Science citation index. The research includes a use case and its corresponding results by using interactive and exploratory network graph representations.

A SEMANTIC APPROACH TO ANALYZE SCIENTIFIC PAPER ABSTRACTS

Each domain and its underlying communities evolve in time and each period is centered on specific topics that emerge from textual sources that characterize the domain. Our analysis represents an extension of other researches performed on the same corpora that were focusing more on evaluating co-citations between the articles in order to compute their importance score (Grauwin and Jensen (1)). Our approach presents a general perspective of the domain by performing semantic comparisons between article abstracts using natural language processing techniques such as Latent Semantic Analysis, Latent Dirichlet Allocation or semantic distances in lexicalized ontologies, i.e. WordNet. Moreover, graph visual representations are generated using Gephi in order to highlight the keywords of each paper and of the domain, the document similarity view or the table of keyword-abstract overlap score. The purpose of the views is to minimize the learning curve of the domain and to facilitate the research process for someone interested in a particular subject. Also, in order to further argue the benefits of our approach, some potential refinements of the methods for classification that can be performed as future improvements are presented.

ReaderBench: A Multi-lingual Framework for Analyzing Text Complexity

Assessing textual complexity is a difficult, but important endeavor, especially for adapting learning materials to students’ and readers’ levels of understanding. With the continuous growth of information technologies spanning through various research fields, automated assessment tools have become reliable solutions to automatically assessing textual complexity. ReaderBench is a text processing framework relying on advanced Natural Language Processing techniques that encompass a wide range of text analysis modules available in a variety of languages, including English, French, Romanian, and Dutch. To our knowledge, ReaderBench is the only open-source multilingual textual analysis solution that provides unified access to more than 200 textual complexity indices including: surface, syntactic, morphological, semantic, and discourse specific factors, alongside cohesion metrics derived from specific lexicalized ontologies and semantic models.

Voice Control Framework for Form Based Applications

Enabling applications with natural language processing capabilities facilitates user interaction, especially in the case of complex applications such as a mobile banking. In this paper we introduce the steps required for building such a system, starting from the presentation of different alternatives alongside their problems and benefits, and ending up with integrating them within our implemented system. However, one of the main problems with voice recognition models is that they tend to use different approximations and thresholds that aren’t completely reliable; therefore, the best solution consists of combining multiple approaches. Consequently, we opted to implement two different and complementary recognition models, and to detail in the end how their integration within the framework’s architecture leads to encouraging results.

Finding the Needle in a Haystack: Who are the Most Central Authors Within a Domain?

The speed at which new scientific papers are published has increased dramatically, while the process of tracking the most recent publications having a high impact has become more and more cumbersome. In order to support learners and researchers in retrieving relevant articles and identifying the most central researchers within a domain, we propose a novel 2-mode multilayered graph derived from Cohesion Network Analysis (CNA). The resulting extended CNA graph integrates both authors and papers, as well as three principal link types: co-authorship, co-citation, and semantic similarity among the contents of the papers. Our rankings do not rely on the number of published documents, but on their global impact based on links between authors, citations, and semantic relatedness to similar articles. As a preliminary validation, we have built a network based on the 2013 LAK dataset in order to reveal the most central authors within the emerging Learning Analytics domain.

Towards an Automated Model of Comprehension (AMoC)

Reading is a complex cognitive process wherein learners acquire new information and consolidate their knowledge. Readers create a mental representation for a given text by processing relevant words that, along with prior inferred concepts, become activated and establish meaningful associations. Our automated model of comprehension (AMoC) uses an automated approach for simulating the ways in which learners read and conceptualize by considering both text-based information consisting of syntactic dependencies, as well as inferred concepts from semantic models. AMoC makes use of cutting edge Natural Language Processing techniques, transcends beyond existing models, and represents a novel alternative for modeling how learners potentially conceptualize read information. This study presents side-by-side comparisons of the results generated by our model versus the ones generated by the Landscape model.

Semantic Meta-search Using Cohesion Network Analysis

Online searching is one of the most frequently performed actions and search engines need to provide relevant results, while maintaining scalability. In this paper we introduce a novel approach grounded in Cohesion Network Analysis in the form of a semantic search engine incorporated in our Hub-Tech platform. Our aim is to help researchers and people unfamiliar with a domain find meaningful articles online, relevant for their project scope. In addition, we integrate state-of-the-art technologies to ensure scalability and low response time, namely SOLR – for data storage and full-text search functionalities – and Akka – for parallel and distributed processing. Preliminary validations denote promising search results, the software being capable to suggest articles in approximately the same way as humans consider them most appropriate – 75% are close results and top 20% are identical to user recommendations. Moreover, Hub-Tech recommended more suitable articles than Google Scholar for our specific task of searching for articles related to a detailed description given as input query (50 + words).

Predicting through writing style the impact of blog posts in online communities

Nowadays blogging has become one of the most common and frequently employed methods for creating communities around specific topics of interest. This phenomenon is due to the existence of numerous online platforms that enable the creation with ease of blogs even for non-technical users. However, finding relevant blogs is a difficult and time-consuming process. This paper focuses on predicting whether a post has an impact or not based only on its writing style and automatically inferred textual complexity indices. We define the impact of a post as the traction it receives from other users in terms of number of received comments. Thus, several blogs were crawled on which a set of textual complexity indices available from the ReaderBench framework were computed. By splitting the posts in two categories, we were able to predict with an accuracy of 69.7% whether a post will receive comments or not.