Survey research is a vital tool for understanding human opinions, behaviors, and preferences, but traditional methods face challenges such as high operational costs, limited sample diversity, and privacy concerns. Large Language Model (LLM)-based agents offer a novel approach to simulate human responses, generating high-quality synthetic data that preserves privacy while enabling researchers to explore patterns in public opinions. Our study introduces a flexible LLM-based survey simulation platform, which personalizes responses using real-world social media data to enhance realism and relevance. We conducted a validation case study using data from Steemit users, comparing the personalized simulated responses generated by LLM agents with actual survey responses collected from these users. This comparative analysis revealed key differences and potential biases, providing insights for refining survey methodologies. Personalized LLM simulations were highly effective for factual questions but faced limitations with subjective topics, often demonstrating lower variance compared to human responses. The quality of social media data and careful model selection also significantly influenced the accuracy of simulations. Our platform enables social science researchers to explore new methodologies for survey design, pre-test the impact of framing, and interact dynamically with LLM agents at reduced cost. This work provides valuable insights into the use of LLM-based agents for enhancing survey research, supporting their application in social science.

In this paper, we propose a full pipeline of analysis of a large corpus about a century of public meeting in historical Australian news papers, from construction to visual exploration. The corpus construction method is based on image processing and OCR. We digitize and transcribe texts of the specific topic of public meeting. Experiments show that our proposed method achieves a F-score of 87.8% for corpus construction. As a result, we built a content search tool for temporal and semantic content analysis.

Although person Re-Identification (ReID) is widely applied in a variety of multimedia systems, most of its essentially multifaceted output is evaluated and visualized inflexibly only using a list of images ranked by the similarity of image content, while the correlations between samples of different IDs and the spatial-temporal features of the images are underinvestigated. As system operators need a comfortable access to these important elements, we introduce an interactive design of a person ReID system to visualize these quantities. We demonstrate that a system offering these visual representations can effectively expedite and improve a person re-identification analysis and make it a much user-friendly experience.

Advances in multimedia analysis, enables access and indexing of huge and rich video content. However, delivering this heterogeneous content remains a challenge. We proposes the use of multiplex networks to combine both textual and visual semantic cues extracted from TV news videos for interactive search refinement on heterogeneous data. After preprocessing, the indexed videos can be queried, for which result space is summarized in a visual cloud helping query refinement with contextual information by combining visual and textual cues. We leverage on properties of multiplex networks to extract a hierarchy of layers, which not only contextualizes results, but also guides the construction of our visual cloud, and its interactions.

One task key to the analysis of large multimedia archive over time is to dynamically monitor the activity of concepts and entities with their interactions. This is helpful to analyze threads of topics over news archives (how stories unfold), or to monitor evolutions and development of social groups. Dynamic graph modeling is a powerful tool to capture these interactions over time, while visualization and finding communities still remain difficult, especially with a high density of links. We propose to extract the backbone of dynamic graphs in order to ease community detection and guide the exploration of trends evolution. Through the graph structure, we interactively coordinate node-link diagrams, Sankey diagrams, time series, and animations in order to extract patterns and follow community behavior. We illustrate our system with the exploration of the role of soccer in 6 years of TV/radio magazines in France, and the role of North Korea in about 10 years of Japanese news.

Multimedia data is by nature heterogeneous, conveying semantic information through multiple cues. Text analysis of closed captions already brought us understanding of the spoken information. Today's advances in computer vision now enable us to look for relevant semantic information from the visual content of real-world archives. Combining these two levels of extracted information to make sense of an archive still remains a challenge. Multiplex net- works, which model multiple families of interactions in a graph, can capture and combine both sources of semantics. We can leverage on these objects to extract hierarchies and integrate them in an interactive heterogeneous "visual cloud". Inspired by word clouds, these clouds allow to grasp visual and textual semantic information captured from a multimedia collection all at once. The interaction then enables direct access to the relevant video. We demonstrate our system with the exploration of a Japanese news archive.