DR. MAHESH, U. HARSHITHA, D SRUTHI, P. ABHIVARDHAN REDDY, J CHAITANYA

Abstract

Inthispaper,weaddresstheissueofautomaticpredictionofreaders’moodfromnewspaperar- ticlesandcomments. Asonlinenewspapersarebecomingmoreandmoresimilartosocialmedia platforms,userscanprovideaffectivefeedback,suchasmoodandemotion.Wehaveexploited theself- reportedannotationofmoodcategoriesobtainedfromthemetadataoftheItalianonline newspaper corriere.it to design and evaluate a system for predicting five different mood cate- gories from news articles and comments: indignation, disappointment, worry, satisfaction, and amusement.Theoutcomeofourexperimentsshowsthatoverall, bag-of-word-ngramsperform better compared to all other feature sets; however, stylometric features perform better for the moodscorepredictionofarticles. Ourstudyshowsthatself-reportedannotationscanbeusedto design automatic mood prediction systems.