Skip to content

Tag: sentiment analysis

Polling social media users to predict election outcomes

Published by Joni on March 30, 2017

The 45th President of the USA Introduction The problem of predicting election outcomes with social media is that the data, such as likes, are aggregate, whereas the election system is not — apart from simple majority voting, in which you only have the classic representativeness problem that Gallup solved in 1936. To solve the aggregation problem, one needs to segment…

Continue readingPolling social media users to predict election outcomes

Analyzing sentiment of topical dimensions in social media

Published by Joni on March 30, 2017

Introduction Had an interesting chat with Sami Kuusela from Underhood.co. Based on that, got some inspiration for an analysis framework which I’ll briefly describe here. The model Figure 1 Identifying and analyzing topical text material The description User is interested in a given topic (e.g., Saara Aalto, or #saaraaalto). He enters the relevant keywords. The system runs a search and…

Continue readingAnalyzing sentiment of topical dimensions in social media

Agile methods for predicting contest outcomes by social media analysis

Published by Joni on March 30, 2017

People think, or seem to assume, that there is some magical machine that spits out accurate predictions of future events from social media data. There is not, and that’s why each credible analysis takes human time and effort. But therein also lies the challenge: when fast decisions are needed, time-taking analyses reduce agility. Real-time events would require real-time analysis, whereas…

Continue readingAgile methods for predicting contest outcomes by social media analysis