slides - CyberEmotions
Transcription
slides - CyberEmotions
www.cyberemotions.eu Collective Emotions in Cyberspace Projective objectives and summary of main results in the second project period 1 Feb.2010 -31. Jan. 2011 In the name of CYBEREMOTIONS Consortium Janusz Hołyst, Project Coordinator, Warsaw University of Technology, [email protected] 1 Collective Emotions in Cyberspace European Union Research Project (FP7 FET) Large-scale integrating project, ICT Call 3 Science of Complex Systems for Socially Intelligent ICT. Duration: 1 Feb. 2009 - 31. Jan. 2013. EC funding 3.6 M€ Participant organisation name Leaders Warsaw University of Technology Janusz Hołyst Ecole Polytechnique Fédérale de Daniel Thalmann Lausanne Stephane Gobron University of Wolverhampton Michael Thelwall Österreichische Studiengesellschaft Robert Trappl Marcin Skowron für Kybernetik Frank Schweitzer ETH Zürich David Garcia Jozef Stefan Institute, Ljubljana Bosiljka Tadic Jacobs University, Bremen Arvid Kappas Technical University Berlin Matthias Trier Gemius SA Anna Borowiec Country Specialization Poland Switzerland Physics of complex systems Virtual reality United Kingdom Webometrics Austria Human‐computer interactions Switzerland Chair of systems design Slovenia Germany Germany Poland Physics of complex networks Psychophysiology Dynamic network analysis Online research agency 2 Twitter revolution Egyptian Revolution: Egyptian protest leader Wael Ghonim’s Twitter message: “congratulations Egypt the criminal has left the palace.” Egypt, Twitter and the Straw Man Revolution ….Twitter is not the root cause of these uprisings. Twitter was not repressed. Twitter did not get inspired by events in other countries. …. Twitter can help organize. Facebook can help get the word out. …. 3 Main project tasks • automatic collection and classification of sentiment data in various e‐communities as well as cross‐ validation of such classifiers using psycho‐physiological methodologies, • qualitative and quantitative sentiment data analysis and data‐driven modeling of collective emotions by ABM, complex networks and fluctuation scaling paradigms, • development of emotionally intelligent ICT tools such as affective dialog systems and graphically animated virtual agents that communicate by emotional interactions. 4 During the second year of its project life CYBEREMOTIONS proved its ambition to be the leading world enterprise in the domain of affective interactions observed in e-communities. CyberEmotions datasets were mentioned in a list of 'The 70 Online Databases that Define our Planet', posted by the Physics arXiv Blog, published by MIT. Main results from the second project period 1. Developing and performing EmoChatting experiments where users had discussions in real time via their avatars with other avatars or simulated agents. The experiments integrated a sentence-based emotion generator and applied graphics engine using models of valence, arousal and dominance for emotional coordinates as well as asymmetric facial expressions. They were carried out by EPFL in close collaboration with OFAI, UW, ETH, WUT, and JUB groups. 2011_wp2_twoYearsSummary.mp4 5 Purpose of WP2 Emotionally reacting active agents (EPFL) Graphics & Emotion • Computer graphical metaphor of emotion applied to Virtual Reality WP specification • Create a virtual society composed of VH, capable of reactions, emotions, and social behavior • Develop interpersonal relationships and nonverbal communication in a virtual society 6 A first CG emotional model {v,a} selection “Hello, nice day!” WP2 WP2 Data mining Classifier WP3 WP2 + 2010_wp2_firstYearS ummary_v2.mov 7 A second CG emotional model VR‐server/clients WP5 WP2 Dynamic event manager Emotional model - Multi user - {v,a,d} - Free interaction - Target - Polarity VH emotional mind, eg.: WP2 - 3D emo. model {v,a,d} Multi classifiers - Memory based on - “SuperClassifier” history of dialogs - “ANEW” WP3 e.g. of dialog WP2 CG animations ‐ Facial and body emotional real‐ time animated interpretations A: “Hello” B: “Hi chick!” A: “What? ” B: “sorry…” A: “It’s ok ” 8 Result: towards a virtual social environment including verbal and non‐verbal communication 9 Austrian Research Institute for Artificial Intelligence – OFAI WP4: acquired data‐sets EmoChatting Dialog system - Virtual Bartender DS <-> WOZ EmoDialog Online Virtual Bartender Role of system’s affective profile 21 IRC channels Same time-frame variety of channels & discussed topics 2200 days of cooperation Long-term online communications between members of Ubuntu communities 2009-2010 Recent “hot topics” of discussion: politics, economy, social issues 10 Austrian Research Institute for Artificial Intelligence – OFAI Affect Listener ‐ Evaluation of Affective Dialog Systems Dialog System vs. Wizard of Oz setting - emotional connection, dialog realism Effect of affective profile in the interaction with a dialog system 11 Austrian Research Institute for Artificial Intelligence – OFAI Virtual Reality settings • Integration of Affect Listener dialog system (OFAI), virtual reality event engine (EPFL) and sentiment classifier (UW) • Comparison of dialog system with WOZ setting • Dialog system results in pair with WOZ ratings • correlation coefficient for DS and WOZ: - chatting enjoyment 0.95 - emotional connection 0.96 - dialog realism 0.97 • no statistically significant differences in the participants ratings 12 13 2. Confirmation of the emergence of collective emotions in cyber‐communities by four project teams applying different methods and using independent datasets (i) (ii) avalanches distribution observed in BBC blogs and Digg data by JSI; non‐random clusters distribution observed in Blogs06, BBC Forum, Digg and IRC channels by WUT; (iii) persistent character of sentiment dynamics observed by ETHZ for IRC channels using the Hurst exponent analysis; (iv) causal sentiment triad distribution found in Network Motif Analysis by TUB. 14 WP6/JSI: Quantitative Analysis of User's Collective Behaviors Mapping the data on bipartite networks: Communities on the networks (Eigenvalue spectral analysis). Time-series analysis and avalanches of positive/negative comments. Accurate mapping of high-resolution data onto bipartite graphs: Users (bulits) and Post&Comments (squares), direction of links indicate user's actions; Color: Emotional content Distribution of sizes of emotional avalanches Indicates Self-Organized Criticality in the dynamics. M. Mitrović, G. Paltoglou and B. Tadić, JSTAT (2011) P02005 WP6/JSI: Agent‐Based Models on Networks Emotional agents – 2D emotional states (arousal, valence); Emotion dynamics on networks; 2 types of AB model on Growing bipartite network Fixed social network Rules of actions and parameters extracted from the Data of Blogs and Diggs and MySpace network. Emotional state of each agent depends his/hers connections on the network. Simulated time-series of charge expressed in comments of 5 communities found on the emergent network: g2 and g3 (with negative charge) continue to grow. M. Mitrović and B. Tadić, DRAFT (2011) WP1, Warsaw Classification based on standard supervised, machine-learning. Emotions e { +1, 0 , -1} hierarchical extension - a document is initially classified by the algorithm as objective or subjective and in the latter case a second-stage classification determines its polarity, either positive or negative. Example discussion +1 0 -1 -1 -1 +1 0 0 +1 -1 We define an emotional cluster of size n as a chain of n consecutive messages with similar sentiment orientations (i.e. negative, positive or neutral). 17 Growth probability for cluster of size n p (e | ne) p (e | e)n The presence of a longer cluster of coherent emotional expressions increases a possibility to follow the cluster by a comment with the same emotion. Conditional probability for cluster growth increases as a power-law with cluster 18 length. 19 Demonstrator CMXViewer (D 8.2) Development of Demonstrator Software CMXViewer (D 8.2): • Animated Graph Visualization representing sentiment propagation processes • Dynamic visualization of longitudinal network data in 2D and 3D showing sentiment dissemination processes • Sentiment-based dynamic link coloring Workpackage 8 (TUB) 20 Sentiment network visualisation (TU Berlin) 21 22 DIGG discussion network (Discussion ID 11223766) rendered with the CMXViewer (TUB) Central component 23 Negative subnetwork 24 Positive subnetwork 25 Sentiment Triad Census Analysis (D 8.3) Workpackage 8 (TUB) 26 Collective emotions of cybercommunities detected by various methods Emotional avalanches Emotional persitence of IRC chatts Hurst eponents t Emotional clusters Sentiment Triad Census Analysis 27 Sentiment Networks Evolution IRC channel interaction network (IRC channel "edubuntu_2007_11") Movies\movie1.wmv Movies\movie2.wmv 28 WP3 Summary (Wolverhampton) 1. SentiStrength algorithm evaluation and improvement‐ detects positive and negative sentiment strength in short informal text 2. Six human classified sentiment strength data sets with >1000 classifications (MySpace, Twitter, BBC, Digg,YouTube, RunnersWorld) 3. Ternary lexicon‐based classifier for social media: Twitter, MySpace, Digg 4. Ordinal prediction of valence and arousal on forum posts: LiveJournal 5. Real‐valued prediction on [1,9] scale of valence/arousal: BBC forum discussions 29 % matching posts An analysis of Twitter sentiment around the top 30 media events showed that increases in interest were typically associated with increases in negative sentiment, even for positive events – such as the oscars #oscars Subj. Sentiment strength 9 Feb 2010 9 Feb 2010 Thelwall, M., Buckley, K., & Paltoglou, G. (2011). Sentiment in Twitter events. Journal of the American Society for Information Science and Technology, 61(12), 2544–2558. Date and time 9 Mar 2010 Increase in negative sentiment strength Date and time 30 9 Mar 2010 Continuous recording of psychophysiology during participation in a forum discussion EMG (smiling, frowning) EKG (heart rate) EDA (sweating) 31 Sample of recording output with a selection of channels EKG (heart rate) EMG (smiling, frowning) Digital online event identifier (“marker”) 32 33 Summary New data sets: • corpora of posts at Twitter and Newsgroups; YouTube • physiological responses after reading and writing emotional posts Confirmation of collective character of emotions in various e‐communities: • BBC blogs and Digg (avalanches) • Blogs06, BBC Forum, Digg and IRC channels by WUT (clustering) • IRC channels (Hurst exponents) • Digg (Motif Analysis) Models of emotions dynamic in cyberecommunities • Agent based models • Stochastic models EmoChatting and EmoDialog experiments • Based on multidimenional emotion models • Applications of avatars or agents • Role of assymetrical facial expressions 34 Collaboration to other Projects and Programmes • Coordination Action ASSYST • Flagship initiative FuturIcT • Flagships Midterm Conference, Warsaw, November 2011 • Proposal Automatic Detection of Affective Mails (ADAM) submitted to Swiss-Polish Research Programme. 35 More results will be presented at Partners presentations 36