Dr Ning Yu is the author of 'LASSA: Emotion Detection via Information Fusion', recently published in the Biomedical Informatics Insights Supplement. We asked Dr Yu to tell us about the background of this paper.

To start please tell us about the challenge this year.  Why did you decide to become involved, and what goals did you and/or your team expect to accomplish?

I have been working on sentiment analysis since 2006 and my Ph.D. dissertation was also in this field. The potential value in suicide prevention and the unique data set were two motivations for me to get involved in this challenge. The suicide notes used in this challenge is the only available data set with annotations on a fine grained level of emotions, thus it is extremely valuable and challenging. Once we can deal with this data set, we can also classify emotions in other areas; for example, help in dialogue systems or in email exchanges with customers to see if the customer gets angry, is satisfied, etc.

What has been the major benefit for you in the work discussed in your article?  How has it contributed to our knowledge of the area?  

This is the first time I have worked with suicide notes. Seeing the potential value of improving common health, I plan to be more actively involved in similar studies. In terms of the contribution of our work, it confirms the robustness of character-based Ngrams for sentiment analysis in a new and more challenging domain and proposes promising future directions.

As many of the articles appearing in the supplement are quick to acknowledge, suicide is a distressingly common cause of death particularly among younger people.  Has this work changed your view of suicide: do you find yourself more or less understanding or sympathetic of people who commit suicide and those they leave behind?  

Definitely! It is sad and depressing to read those notes and I couldn’t help wondering what could have been done to prevent this from happening. After the workshop, I have become more familiar with suicide research and the national effort in suicide prevention. I am touched by the volunteer annotators, who have suffered from losing someone to suicide and are brave enough to participate in the suicide notes annotation. I am glad to know that they find it a relief to help prevent suicide.

View Dr Yu's LinkedIn page here

share on