Abstract
Volcanoes of hate and disrespect erupt in societies often not without fatal consequences. To address this negative phenomenon scientists struggled to understand and analyze its roots and language expressions described as hate speech. As a result, it is now possible to automatically detect and counter hate speech in textual data spreading rapidly, for example, in social media. However, recently another approach to tackling the roots of disrespect was proposed, it is based on the concept of promoting positive behavior instead of only penalizing hate and disrespect. In our study, we followed this approach and discovered that it is hard to find any textual data sets or studies discussing automatic detection regarding respectful behaviors and their textual expressions. Therefore, we decided to contribute probably one of the first human-annotated data sets which allows for supervised training of text analysis methods for automatic detection of respectful messages. By choosing a data set of tweets which already possessed sentiment annotations we were also able to discuss the correlation of sentiment and respect. Finally, we provide a comparison of recent machine and deep learning text analysis methods and their performance which allowed us to demonstrate that automatic detection of respectful messages in social media is feasible.
Highlights
This approach seems to be novel for studies focused on micro-blogging language analysis, because studies aimed at identifying the positive signature behaviors of social media users, with a focus on the use of respectful language or expressions of respect, are difficult to find
This study took the first steps in the “Twitter respectfulness” field by (1) discussing how respect is defined by other authors, (2) creating what is probably the first open Twitter data set annotated with respectfulness labels, and
We found that in our data respectfulness was correlated to sentiment at a moderate level of almost 0.6 which can be interpreted that respect is connected with sentiment, but they are distinguishable notions
Summary
Treating every person with respect [1] seems to be a timeless commandment that everyone would readily agree upon This commandment is not practiced in many societies, groups, and enterprises. The Navy has published a list of signature behaviors that 21st -century sailors should exhibit [1], in which “treating every person with respect” is placed first. This approach seems to be novel for studies focused on micro-blogging language analysis, because studies aimed at identifying the positive signature behaviors of social media users, with a focus on the use of respectful language or expressions of respect, are difficult to find. We hypothesized that the use of polite, respectful language and expressions of respect has been widely discussed in many areas and contexts, not yet regarding Twitter
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
