2017/10/04 by Giannis Haralabopoulos, Haralabopoulos, Giannis, Elena Simperl +1
Computer Science · Physics and Astronomy · #Advanced Text Analysis Techniques #Complex Network Analysis Techniques #Computation and Language (cs.CL) #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #Sentiment Analysis and Opinion Mining
paper · pdf · doi:10.48550/arxiv.1710.04203
openalex publication_date 2017/10/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Sentiment analysis aims to uncover emotions conveyed through information. In\nits simplest form, it is performed on a polarity basis, where the goal is to\nclassify information with positive or negative emotion. Recent research has\nexplored more nuanced ways to capture emotions that go beyond polarity. For\nthese methods to work, they require a critical resource: a lexicon that is\nappropriate for the task at hand, in terms of the range of emotions it captures\ndiversity. In the past, sentiment analysis lexicons have been created by\nexperts, such as linguists and behavioural scientists, with strict rules.\nLexicon evaluation was also performed by experts or gold standards. In our\npaper, we propose a crowdsourcing method for lexicon acquisition, which is\nscalable, cost-effective, and doesn't require experts or gold standards. We\nalso compare crowd and expert evaluations of the lexicon, to assess the overall\nlexicon quality, and the evaluation capabilities of the crowd.\n