Test3

One of the key requirements to facilitate the semantic analytics of information regarding contemporary and historical events on the Web, in the news and in social media is the availability of reference knowledge repositories containing comprehensive representations of events, entities and temporal relations. Existing knowledge graphs, with popular examples including DBpedia, YAGO and Wikidata, focus mostly on entity-centric information and are insufficient in terms of their coverage and completeness with respect to events and temporal relations. In this article we address this limitation, formalise the concept of a temporal knowledge graph and present its instantiation - EventKG. EventKG is a multilingual event-centric temporal knowledge graph that incorporates over 690 thousand events and over 2.3 million temporal relations obtained from several large-scale knowledge graphs and semi-structured sources and makes them available through a canonical RDF representation. Whereas popular entities often possess hundreds of relations within a temporal knowledge graph such as EventKG, generating a concise overview of the most important temporal relations for a given entity is a challenging task. In this article we demonstrate an application of EventKG to biographical timeline generation, where we adopt a distant supervision method to identify relations most relevant for an entity biography. Our evaluation results provide insights on the characteristics of EventKG and demonstrate the effectiveness of the proposed biographical timeline generation method.

Entity Linking (EL) is the task of automatically identifying entity mentions in a piece of text and resolving them to a corresponding entity in a reference knowledge base like Wikipedia. There is a large number of EL tools available for different types of documents and domains, yet EL remains a challenging task where the lack of precision on particularly ambiguous mentions often spoils the usefulness of automated disambiguation results in real applications. A priori approximations of the difficulty to link a particular entity mention can facilitate flagging of critical cases as part of semi-automated EL systems, while detecting latent factors that affect the EL performance, like corpus-specific features, can provide insights on how to improve a system based on the special characteristics of the underlying corpus. In this paper, we first introduce a consensus-based method to generate difficulty labels for entity mentions on arbitrary corpora. The difficulty labels are then exploited as training data for a supervised classification task able to predict the EL difficulty of entity mentions using a variety of features. Experiments over a corpus of news articles show that EL difficulty can be estimated with high accuracy, revealing also latent features that affect EL performance. Finally, evaluation results demonstrate the effectiveness of the proposed method to inform semi-automated EL pipelines.

Entity relatedness has emerged as an important feature in a plethora of applications such as information retrieval, entity recommendation and entity linking. Given an entity, for instance a person or an organization, entity relatedness measures can be exploited for generating a list of highly-related entities. However, the relation of an entity to some other entity depends on several factors, with time and context being two of the most important ones (where, in our case, context is determined by a particular corpus). For example, the entities related to the International Monetary Fund are different now compared to some years ago, while these entities also may highly differ in the context of a USA news portal compared to a Greek news portal. In this paper, we propose a simple but flexible model for entity relatedness which considers time and entity aware word embeddings by exploiting the underlying corpus. The proposed model does not require external knowledge and is language independent, which makes it widely useful in a variety of applications.

Web archiving is the process of collecting portions of the Web to ensure that the information is preserved for future exploitation. However, despite the increasing number of web archives worldwide, the absence of efficient and meaningful exploration methods still remains a major hurdle in the way of turning them into a usable and useful information source. In this paper, we focus on this problem and propose an RDF/S model and a distributed framework for building semantic profiles (“layers”) that describe semantic information about the contents of web archives. A semantic layer allows describing metadata information about the archived documents, annotating them with useful semantic information (like entities, concepts, and events), and publishing all these data on the Web as Linked Data. Such structured repositories offer advanced query and integration capabilities, and make web archives directly exploitable by other systems and tools. To demonstrate their query capabilities, we build and query semantic layers for three different types of web archives. An experimental evaluation showed that a semantic layer can answer information needs that existing keyword-based systems are not able to sufficiently satisfy.

Measuring entity relatedness is a fundamental task for many natural language processing and information retrieval applications. Prior work often studies entity relatedness in static settings and an unsupervised manner. However, entities in real-world are often involved in many different relationships, consequently entity-relations are very dynamic over time. In this work, we propose a neural networkbased approach for dynamic entity relatedness, leveraging the collective attention as supervision. Our model is capable of learning rich and different entity representations in a joint framework. Through extensive experiments on large-scale datasets, we demonstrate that our method achieves better results than competitive baselines.

Publicly available social media archives facilitate research in a variety of fields, such as data science, sociology or the digital humanities, where Twitter has emerged as one of the most prominent sources. However, obtaining, archiving and annotating large amounts of tweets is costly. In this paper, we describe TweetsKB, a publicly available corpus of currently more than 1.5 billion tweets, spanning almost 5 years (Jan'13-Nov'17). Metadata information about the tweets as well as extracted entities, hashtags, user mentions and sentiment information are exposed using established RDF/S vocabularies. Next to a description of the extraction and annotation process, we present use cases to illustrate scenarios for entity-centric information exploration, data integration and knowledge discovery facilitated by TweetsKB.

Archived collections of documents (like newspaper and web archives) serve as important information sources in a variety of disciplines, including Digital Humanities, Historical Science, and Journalism. However, the absence of efficient and meaningful exploration methods still remains a major hurdle in the way of turning them into usable sources of information. A semantic layer is an RDF graph that describes metadata and semantic information about a collection of archived documents, which in turn can be queried through a semantic query language (SPARQL). This allows running advanced queries by combining metadata of the documents (like publication date) and content-based semantic information (like entities mentioned in the documents). However, the results returned by such structured queries can be numerous and moreover they all equally match the query. In this paper, we deal with this problem and formalize the task of "ranking archived documents for structured queries on semantic graphs". Then, we propose two ranking models for the problem at hand which jointly consider: i) the relativeness of documents to entities, ii) the timeliness of documents, and iii) the temporal relations among the entities. The experimental results on a new evaluation dataset show the effectiveness of the proposed models and allow us to understand their limitations.

The Web has evolved to a dominant platform where everyone has the opportunity to express their opinions, to interact with other users, and to debate on emerging events happening around the world. On the one hand, this has enabled the presence of different viewpoints and opinions about a - usually controversial - topic (like Brexit), but at the same time, it has led to phenomena like media bias, echo chambers and filter bubbles, where users are exposed to only one point of view on the same topic. Therefore, there is the need for methods that are able to detect and explain the different viewpoints. In this paper, we propose a graph partitioning method that exploits social interactions to enable the discovery of different communities (representing different viewpoints) discussing about a controversial topic in a social network like Twitter. To explain the discovered viewpoints, we describe a method, called Iterative Rank Difference (IRD), which allows detecting descriptive terms that characterize the different viewpoints (answering the question: what is the viewpoint about?), as well as understanding why a specific term is related to a viewpoint (by detecting other related descriptive terms). The results of an experimental evaluation showed that our approach outperforms state-of-the-art methods on viewpoint discovery, while a qualitative analysis of the proposed IRD method on three different controversial topics showed that IRD provides comprehensive and deep representations of the different viewpoints.

One of the key requirements to facilitate semantic analytics of information regarding contemporary and historical events on the Web, in the news and in social media is the availability of reference knowledge repositories containing comprehensive representations of events and temporal relations. Existing knowledge graphs, with popular examples including DBpedia, YAGO and Wikidata, focus mostly on entity-centric information and are insufficient in terms of their coverage and completeness with respect to events and temporal relations. EventKG presented in this paper is a multilingual event-centric temporal knowledge graph that aims to address this gap. EventKG incorporates over 690 thousand contemporary and historical events and over 2.3 million temporal relations extracted from several large-scale knowledge graphs and less structured sources and makes this information available through a canonical representation. In this paper we present EventKG including its data model, extraction process, and characteristics and discuss its relevance for several real-world applications including Question Answering, timeline generation and cross-cultural analytics.

In this paper we propose a semi-supervised learning strategy to automatically separate fake News from reliable News sources: DistrustRank. We first select a small set of unreliable News, manually evaluated and classified by experts on fact checking portals. Once this set is created, DistrustRank constructs a weighted graph where nodes represent websites, connected by edges based on a minimum similarity between a pair of websites. Next it computes the central- ity using a biased PageRank, where a bias is applied to the selected set of seeds. As an output of the proposed model we obtain a trust (or distrust) rank that can be used in two ways: a) as a counter-bias to be applied when News about a specific subject is ranked, in order to discount possible boosts achieved by false claims; and b) to assist humans to identify sources that are likely to be source of fake News (or that are likely to be reputable), suggesting websites that should be examined more closely or to be avoided. In our experiments, DistrustRank outperforms the supervised approaches in either ranking and classification task.

Recent works in recommendation systems have focused on diversity in recommendations as an important aspect of recommendation quality. In this work we argue that the post-processing algorithms aimed at only improving diversity among recommendations lead to discrimination among the users. We introduce the notion of user fairness which has been overlooked in literature so far and propose measures to quantify it. Our experiments on two diversification algorithms show that an increase in aggregate diversity results in increased disparity among the users.

The amount of multimedia content in the World Wide Web is rapidly growing and contains valuable information for many applications in different domains. The Internet Archive initiative has gathered billions of time-versioned web pages since the mid-nineties. However, the huge amount of data is rarely labeled with appropriate metadata and automatic approaches are required to enable semantic search. Normally, the textual content of the Internet Archive is used to extract entities and their possible relations across domains such as politics and entertainment, whereas image and video content is usually disregarded. In this paper, we introduce a system for person recognition in image content of web news stored in the Internet Archive. Thus, the system complements entity recognition in text and allows researchers and analysts to track media coverage and relations of persons more precisely. Based on a deep learning face recognition approach, we suggest a system that detects persons of interest and gathers sample material, which is subsequently used to identify them in the image data of the Internet Archive. We evaluate the performance of the face recognition system on an appropriate standard benchmark dataset and demonstrate the feasibility of the approach with two use cases.

How did the popularity of the Greek Prime Minister evolve in 2015? How did the predominant sentiment about him vary during that period? Were there any controversial sub-periods? What other entities were related to him during these periods? To answer these questions, one needs to analyze archived documents and data about the query entities, such as old news articles or social media archives. In particular, user generated content posted in social networks, like Twitter and Facebook, can be seen as a comprehensive documentation of our society, and thus, meaningful analysis methods over such archived data are of immense value for sociologists, historians, and other interested parties who want to study the history and evolution of entities and events. To this end, in this paper we propose an entity-centric approach to analyze social media archives and we define measures that allow studying how entities were reflected in social media in different time periods and under different aspects, like popularity, attitude, controversiality, and connectedness with other entities. A case study using a large Twitter archive of 4 years illustrates the insights that can be gained by such an entity-centric and multi-aspect analysis.

Lexical approaches for sentiment analysis like SentiWordNet rely upon a fixed dictionary of words with fixed sentiment, i.e., sentiment that does not change. With the rise of Web 2.0 however, what we observe more and more often is that words that are not sentimental per se, are often associated with positive/negative feelings, for example, "refugees", "Trump", "iphone". Typically, those feelings are temporary as responses to external events; for example, "iphone" sentiment upon latest iphone version release or "Trump" sentiment after USA withdraw from Paris climate agreement. In this work, we propose an approach for extracting and monitoring what we call ephemeral words from social streams; these are words that convey sentiment without being sentimental and their sentiment might change with time. Such sort of words cannot be part of a lexicon like SentiWordNet since their sentiment has an ephemeral character, however detecting such words and estimating their sentiment can significantly improve the performance of lexicon-based approaches, as our experiments show.

Web archives constitute an increasingly important source of information for computer scientists, humanities researchers and journalists interested in studying past events. However, currently there are no access methods that help Web archive users to efficiently access event-centric information in large-scale archives that go beyond the retrieval of individual disconnected documents. In this article, we tackle the novel problem of extracting interlinked event-centric document collections from large-scale Web archives to facilitate an efficient and intuitive access to information regarding past events. We address this problem by: 1) facilitating users to define event-centric document collections in an intuitive way through a Collection Specification; 2) development of a specialised extraction method that adapts focused crawling techniques to the Web archive settings; and 3) definition of a function to judge the relevance of the archived documents with respect to the Collection Specification taking into account the topical and temporal relevance of the documents. Our extended experiments on the German Web archive (covering a time period of 19 years) demonstrate that our method enables efficient extraction of event-centric collections for different event types.

We deal with the problem of ranking news events on a daily basis for large news corpora, an essential building block for news aggregation. News ranking has been addressed in the literature before but with individual news articles as the unit of ranking. However, estimating event importance accurately requires models to quantify current day event importance as well as its significance in the historical context. Consequently, in this paper we show that a cluster of news articles representing an event is a better unit of ranking as it provides an improved estimation of popularity, source diversity and authority cues. In addition, events facilitate quantifying their historical significance by linking them with long-running topics and recent chain of events. Our main contribution in this paper is to provide effective models for improved news event ranking. To this end, we propose novel event mining and feature generation approaches for improving estimates of event importance. Finally, we conduct extensive evaluation of our approaches on two large real-world news corpora each of which span for more than a year with a large volume of up to tens of thousands of daily news articles. Our evaluations are large-scale and based on a clean human curated ground-truth from Wikipedia Current Events Portal. Experimental comparison with a state-of-the-art news ranking technique based on language models demonstrates the effectiveness of our approach.

Longitudinal corpora like legal, corporate and newspaper archives are of immense value to a variety of users, and time as an important factor strongly influences their search behavior in these archives. While many systems have been developed to support users' temporal information needs, questions remain over how users utilize these advances to satisfy their needs. Analyzing their search behavior will provide us with novel insights into search strategy, guide better interface and system design and highlight new problems for further research. In this paper we propose a set of search tasks, with varying complexity, that IIR researchers can utilize to study user search behavior in archives. We discuss how we created and refined these tasks as the result of a pilot study using a temporal search engine. We not only propose task descriptions but also pre and post-task evaluation mechanisms that can be employed for a large-scale study (crowdsourcing). Our initial findings show the viability of such tasks for investigating search behavior in archives.

The Web of Data, and in particular Linked Data, has seen tremendous growth over the past years. However, reuse and take-up of these rich data sources is often limited and focused on a few well-known and established RDF datasets. This can be partially attributed to the lack of reliable and up-to-date information about the characteristics of available datasets. While RDF datasets vary heavily with respect to the features related to quality, provenance, interlinking, licenses, statistics and dynamics, reliable information about such features is essential to enable dataset discovery and selection in tasks such as entity linking, distributed query, search or question answering. Even though there exists a wealth of works contributing to the task of dataset profiling in general, these works are spread across a wide range of communities. In this survey, we provide a first comprehensive overview of the RDF dataset profiling features, methods, tools and vocabularies. We organize these building blocks of dataset profiling in a taxonomy and illustrate the links between the dataset profiling and feature extraction approaches and several application domains. This survey is aimed towards data practitioners, data providers and scientists, spanning a large range of communities and drawing from different fields such as dataset profiling, assessment, summarization and characterization. Ultimately, this work is intended to facilitate the reader to identify the relevant features for building a dataset profile for intended applications together with the methods and tools capable of extracting these features from the datasets as well as vocabularies to describe the extracted features and make them available.

Entity Linking is the task of automatically identifying entity mentions in a piece of text and linking them to their corresponding entries in a reference knowledge base like Wikipedia. Although there is a plethora of works on entity linking, existing state-of-the-art approaches do not explicitly consider the time aspect and specifically the temporality of an entity’s prior probability (popularity) and embedding (semantic network). Consequently, they show limited performance in annotating old documents like news or web archives, while the problem is bigger in cases of short texts with limited context, such as archives of social media posts and query logs. This thesis focuses on this problem and proposes a modeling that leverages time-aware prior probabilities and word embeddings in the entity linking task

We demonstrate BioNex, a system to mine, rank and visualize biomedical news events. BioNex takes biomedical queries such as "Ebola virus disease" and retrieves the k most relevant news events for them. To achieve this we first mine the generic news events by clustering them on a daily basis using general named entities and textual features. These clusters are also tagged with disambiguated biomedical entities which aid in biomedical news event exploration. The clusters are then used to compute the importance scores for the event clusters based on a combination of textual, semantic, popularity and historical importance features. BioNex also visualizes the retrieved event clusters to highlight the top news events and corresponding news articles for the given query. The visualization also provides the context for news events using (1) a chain of historically relevant news event clusters, and (2) other non-biomedical events from the same day.

Web archiving is the process of collecting portions of the Web to ensure that the information is preserved for future exploitation. However, despite the increasing number of web archives worldwide, the absence of efficient and meaningful exploration methods still remains a major hurdle in the way of turning them into a usable and useful information source. In this paper, we focus on this problem and propose an RDF/S model and a distributed framework for building semantic profiles ("layers") that describe semantic information about the contents of web archives. A semantic layer allows describing metadata information about the archived documents, annotating them with useful semantic information (like entities, concepts and events), and publishing all this data on the Web as Linked Data. Such structured repositories offer advanced query and integration capabilities and make web archives directly exploitable by other systems and tools. To demonstrate their query capabilities, we build and query semantic layers for three different types of web archives. An experimental evaluation showed that a semantic layer can answer information needs that existing keyword-based systems are not able to sufficiently satisfy.

Archived collections of documents (like newspaper archives) serve as important information sources for historians, journalists, sociologists and other interested parties. Semantic Layers over such digital archives allow describing and publishing metadata and semantic information about the archived documents in a standard format (RDF), which in turn can be queried through a structured query language (e.g., SPARQL). This enables to run advanced queries by combining metadata of the documents (like publication date) and content-based semantic information (like entities mentioned in the documents). However, the results returned by structured queries can be numerous and also they all equally match the query. Thus, there is the need to rank these results in order to promote the most important ones. In this paper, we focus on this problem and propose a ranking model that considers and combines: i) the relativeness of documents to entities, ii) the timeliness of documents, and iii) the relations among the entities.

Curated web archive collections contain focused digital content which is collected by archiving organizations, groups, and individuals to provide a representative sample covering specific topics and events to preserve them for future exploration and analysis. In this paper, we discuss how to best support collaborative construction and exploration of these collections through the ArchiveWeb system. ArchiveWeb has been developed using an iterative evaluation-driven design-based research approach, with considerable user feedback at all stages. The first part of this paper describes the important insights we gained from our initial requirements engineering phase during the first year of the project and the main functionalities of the current ArchiveWeb system for searching, constructing, exploring, and discussing web archive collections. The second part summarizes the feedback we received on this version from archiving organizations and libraries, as well as our corresponding plans for improving and extending the system for the next release.

Web archives are typically very broad in scope and extremely large in scale. This makes data analysis appear daunting, especially for non-computer scientists. These collections constitute an increasingly important source for researchers in the social sciences, the historical sciences and journalists interested in studying past events. However, there are currently no access methods that help users to efficiently access information, in particular about specific events, beyond the retrieval of individual disconnected documents. Therefore we propose a novel method to extract event-centric document collections from large scale Web archives. This method relies on a specialized focused extraction algorithm. Our experiments on the German Web archive (covering a time period of 19 years) demonstrate that our method enables the extraction of event-centric collections for different event types.

We explore methods to extract relations between named entities from free text in an unsupervised setting. In addition to standard feature extraction, we develop a novel method to re-weight word embeddings. We alleviate the problem of features sparsity using an individual feature reduction. Our approach exhibits a significant improvement by 5.8% over the state-of-the-art relation clustering scoring a F1-score of 0.416 on the NYT-FB dataset.

In order to effectively analyze information regarding ongoing events that impact local communities across language and country borders, researchers often need to perform multilingual data analysis. This analysis can be particularly challenging due to the rapidly evolving event-centric data and the language barrier. In this abstract we present preliminary results of a case study with the goa to better understand how researchers interact with multilingual event-centric information in the context of cross-cultural studies and which methods and features they use.

Social media archives serve as important historical information sources, and thus meaningful analysis and exploration methods are of immense value for historians, sociologists and other interested parties. In this paper, we propose an entity-centric approach to analyze social media archives and we define measures that allow studying how entities are reflected in social media in different time periods and under different aspects (like popularity, attitude, controversiality, and connectedness with other entities). A case study using a large Twitter archive of 4 years illustrates the insights that can be gained by such an entity-centric multi-aspect analysis.