• Kamlesh Lakhwani
• Jeevan Bala

The opinions of people and others are one of the main influencers of human behaviour and activities. Therefore, individuals and organizations often consult with others to understand their opinions or attitudes towards a certain topic, before making decisions. Also, for telecommunication enterprises to survive, they need to be attentive to their customers’ opinions. Sentiment analysis is a technique that is often used by organizations to categorize and understand the underlying attitude of a person towards an entity, product, topic, etc. Though it has been traditionally performed using text-based sources, it has been suggested that other modalities should be explored. One such alternative to text-based sources is video recordings of people using or reviewing content. Videos can contain multiple modals including text, voice, and facial expressions, which can be used to detect a person’s attitude towards a topic. An approach to performing sentiment analysis using affective computing for extracting an opinion holder’s affective data based on their facial expressions, and then feeding this data to a deep learning multilayer perceptron neural network, is proposed in the paper. The outcomes of this study indicate that the proposed approach is highly feasible to gain accurate insights into a person’s sentiment towards a specific topic.

sentiment analysis, social media analytics, deep feedforward neural network, face emotion detection, convolution neural network, data mining, deep learning.

"Deep Learning for Sentiment Analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 10, page no.578-584, October 2018, Available :http://www.jetir.org/papers/JETIRDQ06084.pdf

"Deep Learning for Sentiment Analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 10, page no. pp578-584, October 2018, Available at : http://www.jetir.org/papers/JETIRDQ06084.pdf