Over the past decade, mobile news production has had a growing prevalence and has been established as a new type by modern journalism industry. Journalists understand content capturing and sharing as parts of their role in newsrooms. Mobile journalism (mojo) is an evolving form of reporting in which where people use only a smartphone to create and file stories, and it has been gaining ground during the last decade. This paper aims to examine the difficulties, issues, and challenges in real-world mojo scenarios, analyzing the efficacy of prototype machine-assisted reporting services (MoJo-MATE). A usability evaluation is conducted in quantitative and qualitative terms, paying attention to the media literacy support provided through implemented tools and the proposed collaborations. Students of the School of Journalism and Mass Communications, along with postgraduate-level researchers and professional journalists, form the sample for this investigation, which has a two-folded target: To guide the rapid prototyping process for system development and to validate specific hypotheses by answering the corresponding research questions. The results indicate the impact of mobile/on-demand support and training on journalistic practices and the attitudes of future journalists towards specialized technology in the era of constantly evolving digital journalism.

Social media services make it possible for an increasing number of people to express their opinion publicly. In this context, large amounts of hateful comments are published daily. The PHARM project aims at monitoring and modeling hate speech against refugees and migrants in Greece, Italy, and Spain. In this direction, a web interface for the creation and the query of a multi-source database containing hate speech-related content is implemented and evaluated. The selected sources include Twitter, YouTube, and Facebook comments and posts, as well as comments and articles from a selected list of websites. The interface allows users to search in the existing database, scrape social media using keywords, annotate records through a dedicated platform and contribute new content to the database. Furthermore, the functionality for hate speech detection and sentiment analysis of texts is provided, making use of novel methods and machine learning models. The interface can be accessed online with a graphical user interface compatible with modern internet browsers. For the evaluation of the interface, a multifactor questionnaire was formulated, targeting to record the users’ opinions about the web interface and the corresponding functionality.

No abstract

No abstract

No abstract

Temporal feature integration refers to a set of strategies attempting to capture the information conveyed in the temporal evolution of the signal. It has been extensively applied in the context of semantic audio showing performance improvements against the standard frame-based audio classification methods. This paper investigates the potential of an enhanced temporal feature integration method to classify environmental sounds. The proposed method utilizes newly introduced integration functions that capture the texture window shape in combination with standard functions like mean and standard deviation in a classification scheme of 10 environmental sound classes. The results obtained from three classification algorithms exhibit an increase in recognition accuracy against a standard temporal integration with simple statistics, which reveals the discriminative ability of the new metrics.

No abstract

Radio is evolving in a changing digital media ecosystem. Audio-on-demand has shaped the landscape of big unstructured audio data available online. In this paper, a framework for knowledge extraction is introduced, to improve discoverability and enrichment of the provided content. A web application for live radio production and streaming is developed. The application offers typical live mixing and broadcasting functionality, while performing real-time annotation as a background process by logging user operation events. For the needs of a typical radio station, a supervised speaker classification model is trained for the recognition of 24 known speakers. The model is based on a convolutional neural network (CNN) architecture. Since not all speakers are known in radio shows, a CNN-based speaker diarization method is also proposed. The trained model is used for the extraction of fixed-size identity d-vectors. Several clustering algorithms are evaluated, having the d-vectors as input. The supervised speaker recognition model for 24 speakers scores an accuracy of 88.34%, while unsupervised speaker diarization scores a maximum accuracy of 87.22%, as tested on an audio file with speech segments from three unknown speakers. The results are considered encouraging regarding the applicability of the proposed methodology.