E-ffective: A Visual Analytic System for Exploring the Emotion and Effectiveness of Inspirational Speeches

Abstract

What makes speeches effective has long been a subject for debate, and until today there is broad controversy among public speaking experts about what factors make a speech effective as well as the roles of these factors in speeches. Moreover, there is a lack of quantitative analysis methods to help understand effective speaking strategies. In this paper, we propose E-ffective, a visual analytic system allowing speaking experts and novices to analyze both the role of speech factors and their contribution in effective speeches. From interviews with domain experts and investigating existing literature, we identified important factors to consider in inspirational speeches. We obtained the generated factors from multi-modal data that were then related to effectiveness data. Our system supports rapid understanding of critical factors in inspirational speeches, including the influence of emotions by means of novel visualization methods and interaction. Two novel visualizations include E-spiral (that shows the emotional shifts in speeches in a visually compact way) and E-script (that connects speech content with key speech delivery information). In our evaluation we studied the influence of our system on experts' domain knowledge about speech factors. We further studied the usability of the system by speaking novices and experts on assisting analysis of inspirational speech effectiveness.

SpeechMirror: A Multimodal Visual Analytics System for Personalized Reflection of Online Public Speaking Effectiveness

“…Visualization-centered approaches present the data of presentation techniques through visualizations and further support users in gaining insights through exploration. Existing literature focuses on different purposes of speech analysis: identifying narration strategies [64], understanding emotion [67], training vocal skills [60], analyzing debate transcripts [52], exploring presentation techniques [63], decomposing humor [59], assisting the exploration of gestures [66], and analyzing the effectiveness of different speech factors [32]. While prior works have provided approaches to understand the contributions of speech factors or recommend evidence for public speaking training, our work aims at evaluating a single speech, assisting users to analyze the speech in the context of a speech collection.…”

“…The consulting firm Gartner predicts that by 2024 only 25% of business meetings are offline [46]. In the testing phase of a system including both online and offline speeches, an experienced public speaking expert reasoned that there were significant differences in the emotional expression of online and offline contests [32]. Teodorescu et al [57] found possible differences in NLP (Natural Language Processing) of titles in an online and offline contest, focused on microcontroller applications.…”

“…The complexity of facial expression has led to a variety of visualization strategies to present them. E-ffective used a spiral visualization to show emotional shifts in speakers as well as a text-based visualization to display emotion in the context of a speech script [32]. In EmotionCues, Zeng et al created an Emotion Band, a visualization that allows users to track emotion changes of multiple users in a flow-based design [65].…”

“…However, these tips only give theoretical advice that can be difficult to be used to evaluate or guide practical presentation delivery. For speaking there are inconsistencies between different theories about speech techniques [32,63]. It is time consuming and experience demanding for speakers to understand how their speech performs and even harder to find references for potential improvement.…”

“…The system allows enhanced ability to understand the estimated effectiveness of different techniques in a speech. While various ideas exist for measuring speech effectiveness [32], we utilize a collection of videos ranked in a speech contest as our quantifiable metric. To understand the underlying techniques that influence the effectiveness of online speeches, we establish various multimodal speech factors from domain interviews and existing literature.…”