This demonstration will show how video shot discovery through joint text-video embedding has been integrated into a journalistic workflow through a news monitoring dashboard with the purpose of identifying suitable video material for the creation of immersive scenes around a chosen news story or topic.

This paper explores the current landscape of visualizing large language models (LLMs). The main objective was threefold. Firstly, we investigate how we can visualize LLM-specific techniques such as prompt engineering, instruction tuning, or guidance. Secondly, LLM causality, interpretability, and explainability are examined through visualization. And finally, we showcase the role of visualization in illuminating the integration of multiple modalities. We are interested in discovering the papers that present visualization systems instead of those that use visualization to showcase a part of their work. Our survey aims to synthesize the state-of-the-art in LLM visualization, offering a compact resource for exploring future research avenues.

EVOLVE is a pan-European Innovation Action building a converged infrastructure to bring together the HPC, Cloud, and Big Data worlds. EVOLVE's platform and software stack supports large-scale, data-intensive applications, driven primarily by industry requirements set by pilot and proof-of-concept use cases from diverse fields. Given the unprecedented data growth we are experiencing, EVOLVE's infrastructure is key in enabling the cost-effective processing of massive amounts of data and the adaptation of multiple high-end technologies, in an environment that fosters interoperability and enforces increased security.

This paper investigates the linking of sentiments to their respective targets, a sub-task of fine-grained sentiment analysis. Many different features have been proposed for this task, but often without a formal evaluation. We employ a recursive feature elimination approach to identify features that optimize predictive performance. Our experimental evaluation draws upon two corpora of product reviews and news articles annotated with sentiments and their targets. We introduce competitive baselines, outline the performance of the proposed approach, and report the most useful features for sentiment target linking. The results help to better understand how sentiment-target relations are expressed in the syntactic structure of natural language, and how this information can be used to build systems for fine-grained sentiment analysis.

This paper presents a Web intelligence portal that captures and aggregates news and social media coverage about "Game of Thrones", an American drama television series created for the HBO television network based on George R.R. Martin's series of fantasy novels. The system collects content from the Web sites of Anglo-American news media as well as from four social media platforms: Twitter, Facebook, Google+ and YouTube. An interactive dashboard with trend charts and synchronized visual analytics components not only shows how often Game of Thrones events and characters are being mentioned by journalists and viewers, but also provides a real-time account of concepts that are being associated with the unfolding storyline and each new episode. Positive or negative sentiment is computed automatically, which sheds light on the perception of actors and new plot elements.

This paper presents a novel method for contextualizing and enriching large semantic knowledge bases for opinion mining with a focus on Web intelligence platforms and other high-throughput big data applications. The method is not only applicable to traditional sentiment lexicons, but also to more comprehensive, multi-dimensional affective resources such as SenticNet. It comprises the following steps: (i) identify ambiguous sentiment terms, (ii) provide context information extracted from a domain-specific training corpus, and (iii) ground this contextual information to structured background knowledge sources such as ConceptNet and WordNet. A quantitative evaluation shows a significant improvement when using an enriched version of SenticNet for polarity classification. Crowdsourced gold standard data in conjunction with a qualitative evaluation sheds light on the strengths and weaknesses of the concept grounding, and on the quality of the enrichment process.

Knowledge capture approaches in the age of massive Web data require robust and scalable mechanisms to acquire, consolidate and pre-process large amounts of heterogeneous data, both unstructured and structured. This paper addresses this requirement by introducing the Extensible Web Retrieval Toolkit (eWRT), a modular Python API for retrieving social data from Web sources such as Delicious, Flickr, Yahoo! and Wikipedia. eWRT has been released as an open source library under GNU GPLv3. It includes classes for caching and data management, and provides low-level text processing capabilities including language detection, phonetic string similarity measures, and string normalization.

Novel social media collaboration platforms, such as games with a purpose and mechanised labour marketplaces, are increasingly used for enlisting large populations of non-experts in crowdsourced knowledge acquisition processes. Climate Quiz uses this paradigm for acquiring environmental domain knowledge from non-experts. The game’s usage statistics and the quality of the produced data show that Climate Quiz has managed to attract a large number of players but noisy input data and task complexity led to low player engagement and suboptimal task throughput and data quality. To address these limitations, the authors propose embedding the game into a hybrid-genre workflow, which supplements the game with a set of tasks outsourced to micro-workers, thus leveraging the complementary nature of games with a purpose and mechanised labour platforms. Experimental evaluations suggest that such workflows are feasible and have positive effects on the game’s enjoyment level and the quality of its output.

This paper introduces an interactive news flow visualization that reveals emerging topics in dynamic digital content archives. The presented approach combines several visual metaphors and can be easily adapted to present multi-source social media datasets. In the context of this work, we discuss various methods for improving visual interfaces for accessing aggregated media representations. We combine falling blocks with bar graphs and arcs, but keep these elements clearly separated in different areas of the display. The arc metaphor is adapted and enriched with interactive controls to help users understand the dataset's underlining meaning. The paper describes the implementation of the prototype and discusses design issues with a particular emphasis on visual metaphors to highlight hidden relations in digital content. We conclude with a summary of the lessons learnt and the integration of the visualization component into the Media Watch on Climate Change (www.ecoresearch.net/climate), a public Web portal that aggregates environmental information from a variety of online sources including news media, blogs and other social media such as Twitter, YouTube and Facebook.

Sentiment detection analyzes the positive or negative polarity of text. The field has received considerable attention in recent years, since it plays an important role in providing means to assess user opinions regarding an organization's products, services, or actions. Approaches towards sentiment detection include machine learning techniques as well as computationally less expensive methods. Both approaches rely on the use of language-specific sentiment lexicons, which are lists of sentiment terms with their corresponding sentiment value. The effort involved in creating, customizing, and extending sentiment lexicons is considerable, particularly if less common languages and domains are targeted without access to appropriate language resources. This paper proposes a semi-automatic approach for the creation of sentiment lexicons which assigns sentiment values to sentiment terms via crowd-sourcing. Furthermore, it introduces a bootstrapping process operating on unlabeled domain documents to extend the created lexicons, and to customize them according to the particular use case. This process considers sentiment terms as well as sentiment indicators occurring in the discourse surrounding a articular topic. Such indicators are associated with a positive or negative context in a particular domain, but might have a neutral connotation in other domains. A formal evaluation shows that bootstrapping considerably improves the method's recall. Automatically created lexicons yield a performance comparable to professionally created language resources such as the General Inquirer.

The simplicity of using Web 2.0 platforms and services has resulted in an abundance of user-generated content. A significant part of this content contains user opinions with clear economic relevance - customer and travel reviews, for example, or the articles of well-known and respected bloggers who influence purchase decisions. Analyzing and acting upon user-generated content is becoming imperative for marketers and social scientists who aim to gather feedback from very large user communities. Sentiment detection, as part of opinion mining, supports these efforts by identifying and aggregating polar opinions - i.e., positive or negative statements about facts. For achieving accurate results, sentiment detection requires a correct interpretation of language, which remains a challenging task due to the inherent ambiguities of human languages. Particular attention has to be directed to the context of opinionated terms when trying to resolve these ambiguities. Contextualized sentiment lexicons address this need by considering the sentiment term's context in their evaluation but are usually limited to one domain, as many contextualizations are not stable across domains. This paper introduces a method which identifies unstable contextualizations and refines the contextualized sentiment dictionaries accordingly, eliminating the need for specific training data for each individual domain. An extensive evaluation compares the accuracy of this approach with results obtained from domain-specific corpora.

The World Wide Web has become the world's largest networked information resource, but references to geographical locations remain unstructured and typically implicit in nature. This lack of explicit spatial knowledge within the Web makes it difficult to service user needs for location-specific information. At present, spatial knowledge is hidden in many small information fragments such as addresses on Web pages, annotated photos with GPS co-ordinates, geographic mapping applications, and geotags in user-generated content. Several emerging formats that primarily or secondarily include location metadata, like GeoRSS, KML, and microformats, aim to improve this state of affairs. However, the question remains how to extract, index, mine, find, view, mashup, and exploit Web content using its location semantics. This work-shop brings together researchers from academia and industry labs to discuss and present the latest results and trends in all facets of the relationships between location concepts and Web information.