Ingo Frommholz

Cluster-based polyrepresentation as science modelling approach for information retrieval

AbstractnThe increasing number of publications make searching and accessing the produced literature a challenging task. A recent development in bibliographic databases is to use advanced information retrieval techniques in combination with bibliographic means like citations. In this work we will present an approach that combines a cognitive information retrieval framework based on the principle of polyrepresentation with document clustering to enable the user to explore a collection more interactively than by just examining a ranked result list. Our approach uses information need representations as well as different document representations including citations. To evaluate our ideas we employ a simulated user strategy utilising a cluster ranking approach. We report on the possible effectiveness of our approach and on several strategies how users can achieve a higher search effectiveness through cluster browsing. Our results confirm that our proposed polyrepresentative cluster browsing strategy can in principle significantly improve the search effectiveness. However, further evaluations including a more refined user simulation are needed.

On Textual Analysis and Machine Learning for Cyberstalking Detection

Cyber security has become axa0major concern for users and businesses alike. Cyberstalking and harassment have been identified as axa0growing anti-social problem. Besides detecting cyberstalking and harassment, there is the need to gather digital evidence, often by the victim. To this end, we provide an overview of and discuss relevant technological means, in particular coming from text analytics as well as machine learning, that are capable to address the above challenges. We present axa0framework for the detection of text-based cyberstalking and the role and challenges of some core techniques such as author identification, text classification and personalisation. We then discuss PAN, axa0network and evaluation initiative that focusses on digital text forensics, in particular author identification.

On Clustering and Polyrepresentation

Polyrepresentation is one of the most prominent principles in a cognitive approach to interactive information seeking and retrieval. When it comes to interactive retrieval, clustering is another method for accessing information. While polyrepresentation has been explored and validated in a scenario where a system returns a ranking of documents, so far there are no insights if and how polyrepresentation and clustering can be combined. In this paper we discuss how both are related and present an approach to integrate polyrepresentation into clustering. We further report some initial evaluation results.

Joint Workshop on Bibliometric-enhanced Information Retrieval and Natural Language Processing for Digital Libraries (BIRNDL 2016)

The large scale of scholarly publications poses a challenge for scholars in information-seeking and sensemaking. Bibliometric, information retrieval~(IR), text mining and NLP techniques could help in these activities, but are not yet widely used in digital libraries. This workshop is intended to stimulate IR researchers and digital library professionals to elaborate on new approaches in natural language processing, information retrieval, scientometric and recommendation techniques which can advance the state-of-the-art in scholarly document understanding, analysis and retrieval at scale.

Introduction to the special issue on bibliometric-enhanced information retrieval and natural language processing for digital libraries (BIRNDL)

The large scale of scholarly publications poses a challenge for scholars in information seeking and sensemaking. Bibliometric, information retrievalxa0(IR), text mining, and natural language processing techniques can assist to address this challenge, but have yet to be widely used in digital libraries (DL). This special issue on bibliometric-enhanced information retrieval and natural language processing for digital libraries (BIRNDL) was compiled after the first joint BIRNDL workshop that was held at the joint conference on digital libraries (JCDL 2016) in Newark, New Jersey, USA. It brought together IR and DL researchers and professionals to elaborate on new approaches in natural language processing, information retrieval, scientometric, and recommendation techniques that can advance the state of the art in scholarly document understanding, analysis, and retrieval at scale. This special issue includes 14 papers: four extended papers originating from the first BIRNDL workshop 2016 and the BIR workshop at ECIR 2016, four extended system reports of the CL-SciSumm Shared Task 2016 and six original research papers submitted via the open call for papers.

Classification of colloquial Arabic tweets in real-time to detect high-risk floods

Twitter has eased real-time information flow for decision makers, it is also one of the key enablers for Open-source Intelligence (OSINT). Tweets mining has recently been used in the context of incident response to estimate the location and damage caused by hurricanes and earthquakes. We aim to research the detection of a specific type of high-risk natural disasters frequently occurring and causing casualties in the Arabian Peninsula, namely ‘floods’. Researching how we could achieve accurate classification suitable for short informal (colloquial) Arabic text (usually used on Twitter), which is highly inconsistent and received very little attention in this field. First, we provide a thorough technical demonstration consisting of the following stages: data collection (Twitter REST API), labelling, text pre-processing, data division and representation, and training models. This has been deployed using ‘R’ in our experiment. We then evaluate classifiers’ performance via four experiments conducted to measure the impact of different stemming techniques on the following classifiers SVM, J48, C5.0, NNET, NB and k-NN. The dataset used consisted of 1434 tweets in total. Our findings show that Support Vector Machine (SVM) was prominent in terms of accuracy (F1=0.933). Furthermore, applying McNemar’s test shows that using SVM without stemming on Colloquial Arabic is significantly better than using stemming techniques.

Report on the 3rd International Workshop on Bibliometric-enhanced Information Retrieval (BIR 2016)

To foster collaboration and knowledge transfer between the fields of bibliometrics / scientometrics / informetrics on the one hand and information retrieval on the other hand, we successfully ran a workshop series on bibliometric-enhanced information retrieval (BIR). This workshop report presents the BIR 2016 workshop, which has been co-located with ECIR for the third time this year. We motivate our workshop and outline the papers (one keynote and seven regular papers) presented at ECIR 2016 in Padua, Italy. Finally we reflect on past BIR workshops and conclude with an outlook of future direction.

Bibliometric-Enhanced Information Retrieval: 3rd International BIR Workshop

Bibliometric-enhanced Information Retrieval (BIR) workshops serve as the annual gathering of IR researchers who address various information-related tasks on scientific corpora and bibliometrics. The workshop features original approaches to search, browse, and discover value-added knowledge from scientific documents and related information networks (e.g., terms, authors, institutions, references). We welcome contributions elaborating on dedicated IR systems, as well as studies revealing original characteristics on how scientific knowledge is created, communicated, and used. In this paper we introduce the BIR workshop series and discuss some selected papers presented at previous BIR workshops.

Guest Editors’ introduction to the focussed issue on the 14th European Conference on Digital Libraries (ECDL 2010)

In the 14 years since its first edition back in 1997 the European Conference on Research and Advanced Technology for Digital Libraries (ECDL) has become the reference meeting for an interdisciplinary community of researchers and practitioners whose activity centers around digital libraries. ECDL 2010, the 14th conference in this series, was held in Glasgow, UK, on September 6–10, 2010, following the editions in Pisa (1997), Heraklion (1998), Paris (1999), Lisbon (2000), Darmstadt (2001), Rome (2002), Trondheim (2003), Bath (2004), Vienna (2005), Alicante (2006), Budapest (2007), Aarhus (2008), and Corfu (2009). Aside from being the 14th edition of ECDL, the 2010 edition was also the last. At least with this name, since, starting with 2011, ECDL has been renamed (so as to avoid acronym conflicts with the European Computer Driving License) to TPDL, standing for the Conference on Theory and Practice of Digital Libraries. As we write this editorial, we are looking forward for a successful “first” edition of TPDL, which is going to take place in Berlin in late September 2011. This focussed issue brings together extended versions of six among the best papers of ECDL 2010. The authors of the 12 papers which had been considered the best by the ECDL

The 8th Symposium on Future Directions in Information Access

The 8th PhD Symposium on Future Directions in Information Access (FDIA) will be held in conjunction with the 8th International Conference on the Theory of Information Retrieval (ICTIR 2018) in Tianjin, China. The symposium aims to provide a forum for early stage researchers such as PhD students, to share their research and interact with each other and senior researchers in an informal and relaxed atmosphere. The symposium provides an excellent opportunity for the participants to promote their work and obtain experience in presenting and communicating their research. The participants will learn about different topics in the area of information access and retrieval, receive feedback on their work, meet lots of peers and hear inspiring talks.