Seniz Demir

Information graphics: an untapped resource for digital libraries

Information graphics are non-pictorial graphics such as bar charts and line graphs that depict attributes of entities and relations among entities. Most information graphics appearing in popular media have a communicative goal or intended message; consequently, information graphics constitute a form of language. This paper argues that information graphics are a valuable knowledge resource that should be retrievable from a digital library and that such graphics should be taken into account when summarizing a multimodal document for subsequent indexing and retrieval. But to accomplish this, the information graphic must be understood and its message recognized. The paper presents our Bayesian system for recognizing the primary message of one kind of information graphic (simple bar charts) and discusses the potential role of an information graphics message in indexing graphics and summarizing multimodal documents.

Business model canvas perspective on big data applications

Large and complex data that becomes difficult to be handled by traditional data processing applications triggers the development of big data applications which have become more pervasive than ever before. In the era of big data, data exploration and analysis turned into a difficult problem in many sectors such as the smart routing and health care sectors. Companies which can adapt their businesses well to leverage big data have significant advantages over those that lag this capability. The need for exploring new approaches to address the challenges of big data forces companies to shape their business models accordingly. In this paper, we summarize and share our findings regarding the business models deployed in big data applications in different sectors. We analyze existing big data applications by taking into consideration the core elements of a business (via business model canvas) and present how these applications provide value to their customers by making profit out of using big data.

Exploring and Exploiting the Limited Utility of Captions in Recognizing Intention in Information Graphics

This paper presents a corpus study that explores the extent to which captions contribute to recognizing the intended message of an information graphic. It then presents an implemented graphic interpretation system that takes into account a variety of communicative signals, and an evaluation study showing that evidence obtained from shallow processing of the graphics caption has a significant impact on the systems success. This work is part of a larger project whose goal is to provide sight-impaired users with effective access to information graphics.

Interactive SIGHT into information graphics

Information graphics (such as bar charts and line graphs) play a vital role in many multimodal documents. Unfortunately, visually impaired individuals who use screen reader programs to navigate through such documents have limited access to the graphics. This paper presents the Interactive SIGHT (Summarizing Information GrapHics Textually) system that provides visually impaired individuals with the high-level knowledge that one would gain from viewing graphics in electronic documents. The current system, which is implemented as a browser extension, works on simple bar charts. Once launched by a keystroke combination, Interactive SIGHT first provides a brief initial summary that conveys the underlying message of the bar chart along with the charts most significant features. The system is then able to generate history-aware follow-up responses that provide further information upon request from the user. User evaluations with sighted and visually impaired users showed that the initial summary and follow-up responses are very effective in conveying the informational content of graphics and that the system interface is easy to use.

Generating textual summaries of bar charts

Information graphics, such as bar charts and line graphs, play an important role in multimodal documents. This paper presents a novel approach to producing a brief textual summary of a simple bar chart. It outlines our approach to augmenting the core message of the graphic to produce a brief summary. Our method simultaneously constructs both the discourse and sentence structures of the textual summary using a bottom-up approach. The result is then realized in natural language. An evaluation study validates our generation methodology.

Access to multimodal articles for individuals with sight impairments

Although intelligent interactive systems have been the focus of many research efforts, very few have addressed systems for individuals with disabilities. This article presents our methodology for an intelligent interactive system that provides individuals with sight impairments with access to the content of information graphics (such as bar charts and line graphs) in popular media. The article describes the methodology underlying the systems intelligent behavior, its interface for interacting with users, examples processed by the implemented system, and evaluation studies both of the methodology and the effectiveness of the overall system. This research advances universal access to electronic documents.

Summarizing Information Graphics Textually

Information graphics (such as bar charts and line graphs) play a vital role in many multimodal documents. The majority of information graphics that appear in popular media are intended to convey a message and the graphic designer uses deliberate communicative signals, such as highlighting certain aspects of the graphic, in order to bring that message out. The graphic, whose communicative goal (intended message) is often not captured by the documents accompanying text, contributes to the overall purpose of the document and cannot be ignored. This article presents our approach to providing the high-level content of a non-scientific information graphic via a brief textual summary which includes the intended message and the salient features of the graphic. This work brings together insights obtained from empirical studies in order to determine what should be contained in the summaries of this form of non-linguistic input data, and how the information required for realizing the selected content can be extracted from the visual image and the textual components of the graphic. This work also presents a novel bottom–up generation approach to simultaneously construct the discourse and sentence structures of textual summaries by leveraging different discourse related considerations such as the syntactic complexity of realized sentences and clause embeddings. The effectiveness of our work was validated by different evaluation studies.

Interactive SIGHT: textual access to simple bar charts

Information graphics, such as bar charts and line graphs, are an important component of many articles from popular media. The majority of such graphics have an intention (a high-level message) to communicate to the graph viewer. Since the intended message of a graphic is often not repeated in the accompanying text, graphics together with the textual segments contribute to the overall purpose of an article and cannot be ignored. Unfortunately, these visual displays are provided in a format which is not readily accessible to everyone. For example, individuals with sight impairments who use screen readers to listen to documents have limited access to the graphics. This article presents a new accessibility tool, the Interactive SIGHT (Summarizing Information GrapHics Textually) system, that is intended to enable visually impaired users to access the knowledge that one would gain from viewing information graphics found on the web. The current system, which is implemented as a browser extension that works on simple bar charts, can be invoked by a user via a keystroke combination while navigating the web. Once launched, Interactive SIGHT first provides a brief summary that conveys the underlying intention of a bar chart along with the charts most significant and salient features, and then produces history-aware follow-up responses to provide further information about the chart upon request from the user. We present two user studies that were conducted with sighted and visually impaired users to determine how effective the initial summary and follow-up responses are in conveying the informational content of bar charts, and to evaluate how easy it is to use the system interface. The evaluation results are promising and indicate that the system responses are well-structured and enable visually impaired users to answer key questions about bar charts in an easy-to-use manner. Post-experimental interviews revealed that visually impaired participants were very satisfied with the system offering different options to access the content of a chart to meet their specific needs and that they would use Interactive SIGHT if it was publicly available so as not to have to ignore graphics on the web. Being a language based assistive technology designed to compensate for the lack of sight, our work paves the road for a stronger acceptance of natural language interfaces to graph interpretation that we believe will be of great benefit to the visually impaired community.

Communicative signals as the key to automated understanding of simple bar charts

This paper discusses the types of communicative signals that frequently appear in simple bar charts and how we exploit them as evidence in our system for inferring the intended message of an information graphic. Through a series of examples, we demonstrate the impact that various types of communicative signals, namely salience, captions and estimated perceptual task effort, have on the intended message inferred by our implemented system.

Generating Valence Shifted Turkish Sentences

Valence shifting is the task of rewriting a text towards more/less positively or negatively slanted versions. This paper presents a rule-based approach to producing Turkish sentences with varying sentiment. The approach utilizes semantic relations in the Turkish and English WordNets to determine word polarities and involves the use of lexical substitution and adverbial rules to alter the sentiment of a text in the intended direction. In a user study, the effectiveness of the generation approach is evaluated on real product reviews.