Toward more fine-grained sentiment and emotion analysis of text

Description

When consumers see a piece of text, it can be difficult to know what kinds of sentiment and emotions they associate with it. While there’s a long history of sentiment analysis, Gerard de Melo dives into a series of results on data-driven approaches to provide a more multifaceted and fine-grained understanding of these associations.

Gerard first focuses on sentiment, that is, the methods to detect whether a text is perceived as more positive or negative. The key novelty involves using simple vector representations that capture more fine-grained sentiment information. For instance, the word “hot” is often positive when referring to music, but tends to be negative when referring to the temperature in a hotel room. Using simple techniques, you can create sentiment vector representations that capture such differences between different contexts. These can then readily be exploited by machine learning approaches such as deep neural networks, allowing better analysis of products, hotels, and restaurants, not only in English but in numerous other languages.

You’ll then explore emotions and the perception of text. While there are several psychological theories of emotion, data-driven approaches can provide detailed ratings that reveal to what extent a given word on average evokes a specific emotion. You can then connect these ratings with further data to automatically recommend appropriate fonts and color palettes to use when presenting specific pieces of information. For example, certain fonts and colors are perceived as more exciting, while others are more likely to convey trustworthiness. You’ll then be able to make informed choices that better accord with marketing-based desiderata.

Overall, these methods open up new opportunities for organizations to pay attention to what is being said about them in different markets and to make smarter choices when presenting information to consumers.