- Title
- New data-driven, signaling-based approaches to social media analytics
- Creator
- Lucas, Benjamin James
- Relation
- University of Newcastle Research Higher Degree Thesis
- Resource Type
- thesis
- Date
- 2016
- Description
- Research Doctorate - Doctor of Philosophy (PhD)
- Description
- This thesis explores the construction of brand and consumer signals on social media as they exist in different content forms (e.g. textual, visual). Signaling is explored with reference to social identity theory, and the mechanisms by which signals are created are explored with reference to psycholinguistics and semiotics. Central to this pursuit, this thesis employs cutting-edge data-driven methods to analyse the signaling process as it exists in social media. Specifically, in Study 1 this thesis details new combinations and applications of unsupervised machine learning and graph-based text mining approaches to index and rank terms and brands with reference to signaling. In Study 2 this thesis applies existing image recognition technology to the problem of extracting and indexing relevant and salient themes from visual data (images and video) with reference to signaling. In Study 3, this thesis explores alternative approaches to modelling signaling, using data-driven techniques. Thus, the overarching objective of this thesis is to make contributions to the theoretical development of signaling, with particular reference to the interface between consumer and brand side signaling. Additionally, this thesis contributes to understanding how alternative theoretical lenses can be employed to measure and understand how signals manifest (on both the consumer and brand sides). Secondary to this, this thesis aims to introduce new ways of thinking about how consumer behavior processes are measured, and their manifestations and effects quantified. This is done via the implementation of data-driven analytics techniques to achieve practical outcomes focused on business analytics, business intelligence and business dashboards in a social media context.
- Subject
- social media; data-driven
- Identifier
- http://hdl.handle.net/1959.13/1313689
- Identifier
- uon:22627
- Rights
- Copyright 2016 Benjamin James Lucas
- Language
- eng
- Full Text
- Hits: 504
- Visitors: 1002
- Downloads: 526
Thumbnail | File | Description | Size | Format | |||
---|---|---|---|---|---|---|---|
View Details Download | ATTACHMENT01 | Abstract | 66 KB | Adobe Acrobat PDF | View Details Download | ||
View Details Download | ATTACHMENT02 | Thesis | 2 MB | Adobe Acrobat PDF | View Details Download |