In plain words: Sentiment analysis—telling whether a review is positive or negative—looks nearly solved, so this review checks that claim by tracing the field's progress and mapping its overlooked gaps. It finds the field is far from mature, with deeper understanding of opinions still largely unexplored.
Abstract · Beneath the Tip of the Iceberg: Current Challenges and New Directions in Sentiment Analysis Research
Sentiment analysis as a field has come a long way since it was first introduced as a task nearly 20 years ago. It has widespread commercial applications in various domains like marketing, risk management, market research, and politics, to name a few. Given its saturation in specific subtasks -- such as sentiment polarity classification -- and datasets, there is an underlying perception that this field has reached its maturity. In this article, we discuss this perception by pointing out the shortcomings and under-explored, yet key aspects of this field that are necessary to attain true sentiment understanding. We analyze the significant leaps responsible for its current relevance. Further, we attempt to chart a possible course for this field that covers many overlooked and unanswered questions.
Soujanya Poria, Devamanyu Hazarika, Navonil Majumder, Rada Mihalcea
arXiv:2005.00357 · cs.CL, cs.IR · submitted May 1, 2020 · updated Nov 16, 2020
abstract · pdf · html · Published in the IEEE Transactions on Affective Computing (TAFFC)
