Personal Sense in subjective language research in the blogosphere

Personal Sense in Subjective Language Research


Blogs are a very important part of the digital world, indeed they can be viewed as a digital representation of the whole world. People share pictures and videos, describe their daily life, ask questions and, of course, give opinions. The blogosphere presents a unique opportunity to obtain huge statistics about what people like, feel, need – about their ‘private states’. The vast and ever-growing volumes of ‘bloggers’ and thus, information, demand an automated way of analyzing blog texts.

This gives rise to a new research direction combining computing, linguistics and psychology: sentiment analysis: the computational treatment of (in alphabetical order) opinion, sentiment, and subjectivity in text. Objective characteristics of the writers based on their texts can be analyzed: their age, gender, social affiliation, character; subjective characteristics as moods, negative or positive opinions – polarity, emotions towards an object – can also be investigated.

In the project we argue that individual component of word meaning is an essential phenomenon in subjectivity, and elaborate the notion of Personal Sense to apply it to subjective language investigations. The Personal Sense technique is developed to represent objective characteristics and private states of blog authors. We describe a number of experiments where we demonstrate how more can be said about the author and their private states by harnessing individual Personal Sense; and present a new Personal Sense-based subjectivity, polarity and emotion annotation framework.

  • Synergy Centre at ITT Dublin
  • QQI Brand Logo
  • Member of the Technological University for Dublin Alliance
©2019 Institute of Technology Tallaght • Built by Digital Crew