WWW.IDAIRELAN .COM  


  


 


  


Professor Vincent Wade


                       


T


  


                   





  


      


                                


                            


       


         


RESPONDING TO INDUSTRY NEEDS                    


25 ISSUE 11 CASE STUDY


ADAPT worked withMicrosoft on a tool that can easily moderate user-generated content across languages. The tool ensures that offensive or abusive content is identified quickly, enabling early corrective action. User-generated content has revolutionised the flow of company- customer communication, and companies are now leveraging online content to build brand awareness and generate more engaging business offerings. However, real-time content moderation to identify abusive content is difficult and expensive without a dynamic automated solution. ADAPT and Microsoft identified the need for a scalable solution for moderating user-generated content. By merging expertise, the partners developed a detection platform that will help guide online content moderators to identify offensive user-generated content.


ADAPT experts worked with Microsoft to develop a scalable Offensive Content Detection API that objectively annotates large volumes of offensive content. The detection technology uses natural language parsing, machine learning and interaction analysis to process content and assign an ‘offensiveness’ score. It will facilitate customisation of tolerance thresholds, allowing even obscure offensive content to be flagged for human review.


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53  |  Page 54  |  Page 55  |  Page 56  |  Page 57  |  Page 58  |  Page 59  |  Page 60