180 likes | 300 Views
Emotional Response and Bridging ties on Social Networks Interpreting how Individual Attributes and Social Graph Properties intervene in the Surprise Response in Information Sharing. Carlos Figueiredo. Motivations Overview Research Question Literature Review Research Methods
E N D
Emotional Response and Bridging ties on Social NetworksInterpreting how Individual Attributes and Social Graph Properties intervene in the Surprise Response in Information Sharing Carlos Figueiredo • Motivations • Overview • Research Question • Literature Review • Research Methods • Desired Contributions • Suggestions Digital Media Research Methods Porto, DiMe 24th May 2013
Motivation Make a contribution to solve the problem of the ‘Portfolio Effect’ on Recommender System (e.g. content recommendation). Measurenovelty in aninformationflow. Propose a methodology to measure and predict the delivering of novelty.
Overview RecommenderSystems • CollaborativeFiltering “People like you bought, liked or shared Y” • Trust-BasedCF “People who bought, liked or shared X also bought, liked or shared Y” (1) (2) e.g. Amazon • coding the genome of each song; • listen to other users’ radio stations (Friends, Neighbors, Groups) e.g. Friend Network (Fb); Reputation Network (Ebay) Content-Based “You bought, liked or shared a bunch of things like Y”
Overview Recommenders myproposal Recommendationbasedonnovelty. Noveltydeliveringbasedonusersattributesand in the social graphproperties. Surprise response as a proxyoftheNovelty to design theframework.
Literature Review topicsof research • Noveltydelivering. • Bridgingties • Dimensionsimpliedonnovelty. • Emotional response (Surprise) • Tiestrength (between receptor andsourceofinformation) • Homophily (similarities) • Centrality (structurallocation in the social network)
Literature Review noveltydelivering How to delivernovelty? BridgingTies • TheStrengthofWeakTies(Granovetter 1973) • All bridges are weak ties. Not all weak ties are bridges. • Strong ties can be a bridge if such ties do not share ties with other individuals of the same clique.
Literature Review noveltydelivering Structural Holes and Weak Ties (Burt 1992) • WeaktiesandStructuralholes(McEvily et al. 1999) BridgingTies • StructuralHoles(Burt 1992) • Tie strength does not determine the information potential brought by a bridging tie. • Structural holes linked by actors determine the information potential. • Ties established by non-redundant links between actors.
Literature Review dimensionsimpliedonnovelty Can I predict novelty? Emotional response Ten primordial emotions (DES scale of Izard) (Izard 1991) Emotions start with a process of cognitive appraisal (Finkenauer et al. 1998). Novelty is one fundamental type of appraisal (e.g., Scherer 1984; Smith and Ellsworth 1987). Surprise is a specific consequence of the appraisal of novelty(Finkenaueret al. 1998).
Literature Review dimensionsimpliedonnovelty Whatmakes a tiebestrong? Measuringtiestrength Amount of time, intimacy, intensity and reciprocal services (Granovetter 1973). Closeness (Marsden et al. 1984). Emotional support (Wellman and Wortley 1990). Intensity and valence (Petrosky 2011).
Literature Review dimensionsimpliedonnovelty Why some weakties are not bridges? Homophily • Demographic and Attitudinal similarities • Status homophily • Background factors (economic status), gender, religion and ethnicity(McPherson et al. 2001). • Attitudinal homophily • Perceived Homophily Measure(McCroskey et al. 1975; 2006).
Literature Review dimensionsimpliedonnovelty Homophily • Cognitive similarities based on: • Music genres Reflective and Complex, Intense and Rebellious, Upbeat and Conventional, and Energetic and Rhythmic(Rentfrow and Gosling 2003). • Emotional reaction to music genres. • Similarities on information interests. Similarities on emotional reaction to the information accessed. Equal preferences on content posted (survey).
Literature Review dimensionsimpliedonnovelty Can I predictstructurallocation? Centrality • Degree; betweeness; closeness(Freeman 1979) • Centrality and information flow (Borgattiet al. 2009; Mori et al. 2010) • Centrality and friendship network (Opshal 2010; Afuah 2013)
Research questions Does surprise define bridging ties? Can similarities in individual attributes and structural location in the network determine the stimulus of surprise?
Hypothesis H1 – Is more likely that an individual become surprised by a weak tie than by a strong tie. H2 – The non redundancy between ties is predictor of surprise. H3 – The degree of homophily justifies the conditions that make someone weakly tied to another person acting as a bridge. H4 – Users' popularity is independent of the novelty appraisal by the receptors.
Research Methods • Survey • Emotional response, particularly on surprise • Tiesstrength • Homophily • SPSS • Statistics (Logistic regression; Multivariate regression; Mann-Whitney test)
Research Methods • NodeXl • Centralityvariables (degree; betweeness; closeness) • Graph 2 – Friendship network • Graph 1 - Emotional reaction to information sharing
Desired contribution • Emotional reaction as a relevant property for social networks analysis. • A methodology that identifies bridging ties and characterizes the delivering of novelty based in the stimulus of surprise. • A framework for recommendation systems based on weak ties as recommenders of surprising information or of new perspectives.
Suggestions • Comments are welcome… • Thank you. Carlos Figueiredo