Facet Embeddings for Explorative Analytics in Digital Libraries

Mesbah, Sepideh; Fragkeskos, Kyriakos; Lofi, Christoph; Bozzon, Alessandro; Houben, Geert‐Jan

doi:10.1007/978-3-319-67008-9_8

Cited by 7 publications

(13 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SmartPub integrates results from our previous work [5,6], and extends them as depicted in Figure 2. Starting from a seed set of instances of the targeted entity type (e.g.…”

Section: Ner/netmentioning

confidence: 54%

“…Experiments [5,6] shown that our approach can provide good quality results in terms of precision/recall/fscore for the dataset entity type (0.77/0.30/0.43) compared to BS (0.08/0.13/0.10) and for the method entity type (0.68/0.15/0.25) compared to BS (0.11/0.32/0.16), with a seed set of 100 entities. We infer that different expansion strategies augment the performance of our technique compared to the BS which just relies on features such as unigrams, bigrams, closest verb, etc.…”

Section: Ner/netmentioning

confidence: 99%

See 1 more Smart Citation

SmartPub

Mesbah

Bozzon

Lofi

et al. 2018

Companion of the the Web Conference 2018 on the Web Conference 2018 - WWW '18

Self Cite

View full text Add to dashboard Cite

This demo presents SmartPub, a novel web-based platform that supports the exploration and visualization of shallow meta-data (e.g., author list, keywords) and deep meta-data -long tail named entities which are rare, and often relevant only in specific knowledge domain -from scientific publications. The platform collects documents from different sources (e.g. DBLP and Arxiv), and extracts the domain-specific named entities from the text of the publications using Named Entity Recognizers (NERs) which we can train with minimal human supervision even for rare entity types. The platform further enables the interaction with the Crowd for filtering purposes or training data generation, and provides extended visualization and exploration capabilities. SmartPub will be demonstrated using sample collection of scientific publications focusing on the computer science domain and will address the entity types Dataset (i.e. dataset presented or used in a publication), and Methods (i.e. algorithms used to create/enrich/analyse a data set).

show abstract

“…SmartPub integrates results from our previous work [5,6], and extends them as depicted in Figure 2. Starting from a seed set of instances of the targeted entity type (e.g.…”

Section: Ner/netmentioning

confidence: 54%

Section: Ner/netmentioning

confidence: 99%

SmartPub

Mesbah

Bozzon

Lofi

et al. 2018

Companion of the the Web Conference 2018 on the Web Conference 2018 - WWW '18

Self Cite

View full text Add to dashboard Cite

show abstract

“…They do not leverage the user perspective on the scientific literature. As a result, the most relevant documents against a cluster are often missed out, that actually best match in accordance to users' perception (Mesbah et. al., 2017).…”

Section: Introductionmentioning

confidence: 85%

Tweet Coupling: a social media methodology for clustering scientific publications

et al. 2020

View full text Add to dashboard Cite

We argue that classic citation-based scientific document clustering approaches, like co-citation or bibliographic coupling, lack to leverage the social-usage of the scientific literature originate through online information dissemination platforms, such as Twitter. In this paper, we present the methodology tweet coupling, which measures the similarity between two or more scientific documents if one or more Twitter users mention them in the tweet(s). We evaluate our proposal on an altmetric dataset, which consists of 3,081 scientific documents and 8,299 unique Twitter users. By employing the clustering approaches of bibliographic coupling and tweet coupling, we find the relationship between the bibliographic and tweet coupled scientific documents. Further, using VOSviewer, we empirically show that tweet coupling appears to be a better clustering methodology to generate cohesive clusters since it groups similar documents from the subfields of the selected field, in contrast to the bibliographic coupling approach that groups cross-disciplinary documents in the same cluster.

show abstract

“…In the context of digital libraries, there is a plethora of related work on learning and applying representations for documents. High-dimensional vector representations are utilised in explainable models to interactively gather insights into a digital library [36,37], for visual search interfaces [25,34,38], as well as for interactive clustering or classification [11,12]. Visualisations, such as overview maps of an entire digital library, are powerful tools to explore the data [15].…”

Section: Introductionmentioning

confidence: 99%

Interactive Curation of Semantic Representations in Digital Libraries

Repke¹,

Krestel²

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Digital libraries often contain many heterogeneous documents and cover a variety of topics. Computer generated virtual maps of such collections can help to get an overview and explore the data. The position of each document from the corpus on this virtual two-dimensional map is determined by its semantic similarity to the other documents. However, the computed layout of the data may not adhere to the expectation of domain experts. To this end, we propose a novel approach that enables users to interactively curate the layout of the data. By dragging only a few documents on the canvas, the user can adjust the computed layout to better reflect the expected interpretation of the underlying data. We demonstrate the effectiveness and robustness of our approach using a series of real world datasets.

show abstract

Facet Embeddings for Explorative Analytics in Digital Libraries

Cited by 7 publications

References 16 publications

SmartPub

SmartPub

Tweet Coupling: a social media methodology for clustering scientific publications

Interactive Curation of Semantic Representations in Digital Libraries

Contact Info

Product

Resources

About