EmoWrite: A Sentiment Analysis-Based Thought to Text Conversion

Abstract

Brain-Computer Interface (BCI) helps in processing and extraction of useful information from the acquired brain signals having applications in diverse fields such as military, medicine, neuroscience and rehabilitation. BCI has been used to support paralytic patients having speech impediments with severe disabilities. To help paralytic patients communicate with ease, BCI based systems convert silent speech (thoughts) to text. However, these systems have an inconvenient graphical user interface, high latency, limited typing speed and low accuracy rate. Apart from these limitations, the existing systems do not incorporate the inevitable factor of patient's emotional states and sentiment analysis. The proposed system “EmoWrite” implements a dynamic keyboard with contextualized appearance of characters reducing the traversal time and improving the utilization of the screen space. A novel scheme is proposed to integrate the prediction of contextualized words with the mental state by addressing the challenge of accurate class detection, as there is a slight difference between emotional classes i.e. happiness, sadness, anger and calm. EmoWrite effectively lists the helping verbs related to previously typed text within an acceptable time to improve the typing speed. The display of the character set on the keyboard, prediction of words and articles are personalized for each individual and evolve with time. The proposed system also helps a medical practitioner in the record-keeping of emotional states to keep track of a patient’s progress and plan treatment accordingly. The proposed system has been evaluated and compared with the existing systems for accuracy, convenience, sentimental analysis and typing speed. This system results in 6.58 Words Per Minute (WPM) and 31.92 Characters Per Minute (CPM) which accuracy of 90.36%. EmoWrite also shows remarkable results when it comes to the integration of emotional states. Its Information Transfer Rate (ITR) is also high as compared to other systems i.e. 87.55 bits/min with commands and 72.52 bits/min for letters. Furthermore, it provides ease to use interface with a latency of 2.685 sec.