Lyndon Nixon
Short Bio
Dr Nixon is an Assistant Professor in the Department of Applied Data Science. His research interests cover the visual classification of photography to automatically extract the touristic destination image from social networks such as Instagram; the use of deep learning for predictive analytics in open domains such as predicting the next trending topic in online channels; the extraction and modelling of knowledge, e.g. about events, in graph structures and their combination with neural networks to improve computational understanding of the world.
He also leads research projects at the Research Centre for New Media Technology in his role as CTO of MODUL Technology GmbH, the research spin-off of MODUL University. He was project coordinator of the EU Horizon 2020 project ReTV (www.retv-project.eu), which developed tools to help media organisations to optimally select and repurpose their media assets for digital marketing. He led research in predicting future trending topics among online audiences and recommending relevant future events to target in online marketing. He also coordinates the FFG project EPOCH (extracting and predicting events from online communication; www.epoch-project.eu) and participates in the BMVIT project EcoMove (prediction of urban mobility bottlenecks; www.ecomove.at) and the FFG project GENTIO (prediction of future communication success of online publications; www.gentio.eu).
Previously he has been active in the EU projects InVID (finding and verifying fake news video on social networks; www.invid-project.eu) and LinkedTV (identifying topics of TV programming and linking them to related Web content on a second screen; www.linkedtv.eu).
Dr Nixon welcomes thesis and research project proposals around any of the above topics!
Research Interests
His research domain is the analysis and description of online media and the use of this description in the computational understanding and use of media assets, supported by knowledge models in graph-based structures ("knowledge graphs") to provide additional explicit understanding of the domain.
He works in the domains of e-tourism ("Visual Destination Image" - extracting tourist destination image from online photography), news and journalism (video verification based on visual content and knowledge models), and media organisations and broadcasters ("TV Intelligence" - extracting additional information from and around audiovisual streams to enhance their re-use).
Projects
-
GENTIO - Generative Learning Networks for Text and Impact Optimization
GENTIO aims for radical innovation in the way we produce, enrich and analyse digital content. The project will develop a flexible Deep Learning Architecture to unify the understanding of text at three fundamental levels: structure, content and context. The first use case targets the marketing domain. It will experiment with new methods for communication experts to maximize the impact of data-driven publishing. The second use case targets the news media sector, automatically correcting and classifying noisy output from Optical Character Recognition (OCR) systems - using topics extracted from the public debate on other microblogging sites to obtain the required context information.
Organisations: MODUL University Vienna, Department of New Media Technology
Author: Lyndon Nixon, Adrian Brasoveanu, Jakob Steixner
Date: 01.01.2020 - 31.12.2022
Managed By: MODUL University Vienna
-
Carrying Capacity Methodology for Tourism
The overall goal of the service contract is to determine the carrying capacity in regions dominated by tourism. This will help local leaders in destinations to analyse and assess the impact of tourism in their regions based on indicators for the economic, social and environmental aspects affected. The focus will lie on big data, new technologies, artificial intelligence and high-performance computing. This needs to be conditioned for European tourist destinations. In the context of this service contract local, national and EU policies will be advised in managing and measuring carrying capacity in tourist destinations.
Organisations: MODUL University Vienna, Department of Sustainability, Governance, and Methods, Department of Public Governance and Sustainable Development, Department of Tourism and Service Management, Department of New Media Technology
Author: Sabine Sedlacek, Christian Weismayer, Bozana Zekan, Ulrich Gunter, Daniel Dan, Lyndon Nixon
Date: 11.11.2019 - 11.11.2020
Managed By: MODUL University Vienna
-
Qualifikationsnetzwerk "Smart Data Analytics für die Hotellerie"
The purpose of the qualification network is to teach employees of tourism businesses - especially accommodation providers - the use of data and advanced methods of analysis. Data management and analysis is considered a central element of digitalization in tourism and the added value of an efficient and effective data processing is given in the companies. The aim is to teach the state of research in a way that enables businesses to explore new sources of data and to link these sources to generate better information for decision-making. With this knowledge, businesses should be better able to accompany and to consult the guest during the whole "customer-journey". For this purpose, the scientific partners MODUL University Vienna and Technical University Vienna combine their expertise in the area of data management and tourism.
Organisations: Department of Tourism and Service Management, MODUL University Vienna, Department of New Media Technology
Author: Hannes Antonschmidt, Astrid Dickinger, Ulrich Gunter, Lyndon Nixon, Daniel Dan, Arno Scharl
Date: 01.07.2019 - 31.12.2020
Managed By: Department of Tourism and Service Management
-
EPOCH - Extracting and Predicting Events from Online Communication and Hybrid Datasets
EPOCH will measure the effects on statistical indicators of events being reported in the news and social media. Innovatively, it will use the measured effects of now past events to predict the future changes expected due to future events detected in the public dialogue. Through the EPOCH dashboard, organizations can identify and thus better prepare for these changes, adapting their communications, marketing and resources accordingly. This will be demonstrated in the domains of purchase price forecasting and public relations.
Organisations: MODUL University Vienna, Department of New Media Technology, Department of Sustainability, Governance, and Methods
Author: Lyndon Nixon, Sabine Sedlacek, Ivo Ponocny, Adrian Brasoveanu, Jakob Steixner
Date: 01.01.2019 - 31.12.2021
Managed By: Modul Technology GmbH
-
ReTV - Enhancing and Repurposing TV Content for Trans-Vector Engagement
ReTV aims to provide broadcasters and content distributors with technologies and insights to leverage the converging digital media landscape. By advancing the state of the art in the analysis of this media landscape and providing novel methods to dynamically re-purpose content for an array of media vectors (= all relevant digital channels), a Trans-Vector Platform (TVP) will provide these stakeholders with the ability to "publish to all media vectors with the effort of one". It will empower broadcasters and brands to measure and predict the success of their content and advertisments in terms of reach and audience engagement across vectors.
Organisations: MODUL University Vienna, Department of New Media Technology, Modul Technology GmbH
Author: Lyndon Nixon, Adrian Brasoveanu, Jakob Steixner, Adriana Bassani, Pavel Filippov, Maximilian Lang, Rod Michael Coronel
Date: 01.01.2018 - 31.12.2020
Managed By: Modul Technology GmbH
-
EcoMove
EcoMove will develop new knowledge-based solutions for the efficient and environmentally sustainable movement of users in cities. This will be achieved by providing customised information about available mobility options in real time. Recommendations for delaying, avoiding or taking alternative mobilty options will be presented visually to the users - city inhabitants, visitors, and professional stakeholders - for the purpose of prioritizing "necessary" mobility. Vienna will be the city test case; the developed methods will be generic and the data collection will cover the entirety of Austria so that an extended application of the solutions to other regions as part of future projects will also be possible.
Organisations: MODUL University Vienna, Department of New Media Technology, Department of Tourism and Service Management
Author: Lyndon Nixon, Astrid Dickinger, Sabine Sedlacek, Daniel Dan
Date: 01.07.2018 - 30.06.2020
Managed By: MODUL University Vienna
-
InVID – In Video Veritas
In video veritas, if we divert the old Latin saying: In video, there is truth! The digital media revolution and the convergence of social media with broadband wired and wireless connectivity are bringing breaking news to online video platforms; and, news organisations delivering information by Web streams and TV broadcast often rely on user-generated recordings of breaking and developing news events shared by social media to illustrate the story. However, in video there is also deception. Access to increasingly sophisticated editing and content management tools, and the ease in which fake information spreads in electronic networks requires reputable news outlets to carefully verify third-party content before publishing it, reducing their ability to break news quickly while increasing costs in times of tight budgets. InVID will build a platform providing services to detect, authenticate and check the reliability and accuracy of newsworthy video files and video content spread via social media. This platform will enable novel newsroom applications for broadcasters, news agencies, web pure-players, newspapers and publishers to integrate social media content into their news output without struggling to know if they can trust the material or how they can reach the user to ask permission for re-use. It will ensure that verified and rights-cleared video content is readily available for integration into breaking and developing news reports. Validated by real customer pilots, InVID will help protecting the news industry from distributing fakes, falsehoods, lost reputation and … lawsuits.
Organisations: Modul Technology GmbH
Author: Lyndon Nixon
Date: 01.01.2016 - 31.12.2018
Managed By: Modul Technology GmbH
-
MediaMixer
The main rationale of MediaMixer is to set up and sustain a community of video producers, hosters, and redistributors who will be supported in the adoption of semantic multimedia technology in their systems and workflows to build a European market for media fragment re-purposing and re-selling. While we have already established, traditional markets for complete videos, e.g. in stock footage portals, media libraries or TV archives, where entire videos may be found and also purchased for re-use in new media production situations, these markets do not permit the easy purchase or sale of smaller fragments of AV materials.The MediaMixer CA will address this deficit by showing the vision of a media fragment market (the MediaMixer) to the European media production, library, TV archive, news production, e-learning and UGC portal industries. We will demonstrate the achievable benefits enabled by the creation, repurposing and reuse of digital contents across borders on the Web, where media fragments are intelligent digital objects, identified and classified at a highly granular degree, integrated with knowledge management, and connected at Web-scale. The objective of MediaMixer is to set up and sustain a community of video producers, hosters, and redistributors who will be supported in the adoption of semantic multimedia technology in their systems and workflows to build a European market for media fragment re-purposing and reselling. Networking with the community will ensure that research results and technology development truly meets the industry requirements and reflects real world use cases. Demonstrators in media production, news reporting and e-learning will highlight the technology value, with a wider impact achieved through the support of media industry experts and associations to present these results to their members. A number of events will be organised to network the industry members with the research experts of MediaMixer and facilitate technology transfer (by information days and training), and an online portal will drive the geographically distributed community and act as a central access point to tools, materials, use cases, demos and presentations.
Organisations: MODUL University Vienna, Department of New Media Technology
Author: Lyndon Nixon
Date: 01.11.2012 - 30.04.2014
Managed By: Department of New Media Technology
-
LinkedTV
The project is an integrated and practical approach towards experiencing Networked Media in the Future Internet. The Web’s original success was the underlying hypertext paradigm built into HTML. Hypermedia has been pursued for quite a while as an extension of the hypertext approach towards video information. But it needs complex video analysis algorithms and is still an issue of research. Television Linked To The Web (LinkedTV) provides a novel practical approach to Future Networked Media. It is based on four phases: annotation, interlinking, search, and usage (including personalization, filtering, etc.). The result will make Networked Media more useful and valuable, and it will open completely new areas of application for Multimedia information on the Web. After 42 months of research and development completed by 12 partners across Europe, the LinkedTV project has produced services, tools and documents, enabling a new generation of TV applications. From the beginning, the project aimed at making the vision of Linked Television become reality. Linked Television is the seamless interweaving of TV and Web content into a single, integrated experience. It is watching the news and getting background information on the stories; it is seeing a painting in a TV programme and identifying the artist and the museum where it hangs. LinkedTV is making this possible and cost-effective for content owners and broadcasters by offering a Platform, which handles the complete end-to-end workflow of video analysis and enrichment as well as personalising to each viewer. The innovative technology identifies the concepts and topics in the TV programme, as well as selecting the most appropriate information and content to present for each concept and topic. Manual curation checks and complements the accuracy of the automated services. Dedicated client applications can be built retrieving the programme enrichments from the Platform, eased by using LinkedTV’s developer toolkit to handle presentation on and synchronisation across screens and devices. The LinkedTV technology is based on research results that extended the state-of-the-art in many areas. New algorithms and methods for automatic decomposition of audiovisual content, the association of content segments with objects and scene labels, text and audio analysis and event and instance-based labelling of content segments have been developed to provide annotations on fragment level. The annotated media fragments are further enhanced by methods of named entitiy recognition and enriched with additional content discovered by Web mining approaches. Research on personalisation and contextualisation resulted in technologies that ensure the relevance of the enrichments for the consumer. With several in-depth user studies the project gathered valuable insights on the interests of TV consumers. This knowledge and also the acquired experience in tool development and platform management are exploited by LinkedTV partners in future projects and consultancy offers. Research results, knowledge and the LinkedTV technology were already successfully shown at events like IFA and IBC and will be further disseminated in future publications, at conferences and workshops, industry events and exhibitions.
Organisations: MODUL University Vienna, Department of New Media Technology
Author: Lyndon Nixon
Date: 01.10.2013 - 31.03.2015
Managed By: MODUL University Vienna
Research Output
- 2020
-
"In Media Res: A Corpus for Evaluating Named Entity Linking with Creative Works"2020 Pages: 355-364
Annotation styles express guidelines that direct human annotators in what rules to follow when creating gold standard annotations of text corpora. These guidelines not only shape the gold standards they help create, but also influence the training and evaluation of Named Entity Linking (NEL) tools, since different annotation styles correspond to divergent views on the entities present in the same texts. Such divergence is particularly present in texts from the media domain that contain references to creative works. In this work we present a corpus of 1000 annotated documents selected from the media domain. Each document is presented with multiple gold standard annotations representing various annotation styles. This corpus is used to evaluate a series of Named Entity Linking tools in order to understand the impact of the differences in annotation styles on the reported accuracy when processing highly ambiguous entities such as names of creative works. Relaxed annotation guidelines that include overlap styles lead to better results across all tools.
Author(s): Lyndon Nixon, Adrian Brasoveanu, Albert Weichselbraun
Publication date: 19. 11. 2020
Pages: 355-364
-
"Predicting your future audience’s popular topics to optimize TV content marketing success"2020 Pages: 5-10
TV broadcasters and other organizations with online media collections which wish to extend the reach of and engagement with their media assets conduct digital marketing activities. The marketing success depends on the relevance of the topics of the media content to the audience, which is made even more difficult when planning future marketing activities as one needs to know the topics that the future audience will be interested in. This paper presents the innovative application of AI based predictive analytics to identify the topics that will be more popular among future audiences and its use in a digital content marketing strategy of media organisations.
Author(s): Lyndon Nixon
Publication date: 12. 10. 2020
Pages: 5-10
Electronic version(s), related files and links: http://dx.doi.org/10.1145/3422839.3423062
-
"Predicting Your Future Audience: Experiments in Picking the Best Topic for Future Content"2020 Pages: 185-188
This work in progress reports on ongoing experimentation with machine learning approaches on time series data, where the time series is a quantification of the success of content about a certain topic published on a certain digital channel over a past time period. The experiment tests how accurate predictive analytical approaches can be to predict the future success of a piece of media content published on the Web or social media platform according to its topics. Our intention is to enable a new innovation in media organizations’ content publication strategies, where the choice of media for a future publication can be informed by such predictive capabilities in order to maximize the potential content's reach to a digital audience.
Author(s): Lyndon Nixon
Publication date: 17. 6. 2020
Pages: 185-188
Electronic version(s), related files and links: http://dx.doi.org/10.1145/3391614.3399398
-
"Topics Compass: uncovering Trending Topics for Optimised Media Content Publication"2020
Author(s): Lyndon Nixon, Arno Scharl, Rasa Bocyte
Publication date: 14. 6. 2020
-
"Automatic Expansion of Domain-Specific Affective Models for Web Intelligence Applications"2020 in: Cognitive Computation.
Background. Sentic computing relies on welldefined affective models of different complexity - polarity to distinguish positive and negative sentiment,
for example, or more nuanced models to capture expressions of human emotions. When used to measure
communication success, even the most granular affective model combined with sophisticated machine learning approaches may not fully capture an organisation’s
strategic positioning goals. Such goals often deviate from
the assumptions of standardised affective models. While
certain emotions such as Joy and Trust typically represent desirable brand associations, specific communication goals formulated by marketing professionals often
go beyond such standard dimensions. For instance, the
brand manager of a television show may consider fear
or sadness to be desired emotions for its audience.
Method. This article introduces expansion techniques
for affective models, combining common and commonsense knowledge available in knowledge graphs with
language models and affective reasoning, improving coverage and consistency as well as supporting domainspecific interpretations of emotions.
Results and Conclusions. An extensive evaluation
compares the performance of different expansion techniques: (i) a quantitative evaluation based on the revisited Hourglass of Emotions model to assess perfor
mance on complex models that cover multiple affective categories, using manually compiled gold standard
data, and (ii) a qualitative evaluation of a domainspecific affective model for television programme brands.
The results of these evaluations demonstrate that the
introduced techniques support a variety of embeddings
and pre-trained models. The paper concludes with a
discussion on applying this approach to other scenarios
where affective model resources are scarce.Author(s): Albert Weichselbraun, Jakob Steixner, Adrian Brasoveanu, Arno Scharl, Max Göbel, Lyndon Nixon
Publication date: 2020
Electronic version(s), related files and links: http://dx.doi.org/10.1007/s12559-021-09839-4
Load more results
