Sentiment Analysis is considered to be the “flagship” service of web service and social media monitoring, as it is the basis of a number of important alerts / notifications, published in real time, that are crucial for the client.
We have managed to achieve up to 90% precision in sentiment analysis, backed by skilled and experienced Data Scientists and Data Analysts, and having developed distinct models of customer sentiment prediction in the Greek language.
Sentiment analysis is applied over entities (companies, agencies, individuals, products), which are mentioned in the texts with a positive, negative or neutral characterization. Our algorithms are able to identify the different entities mentioned in a text, distinguish the various writings of an entity (e.g. full name of a company or its initials) and emotionally charged words that express a positive or negative opinion to them. Using syntactic analysis we are also able to decide on the emotional power of the text and consequently to aggregate opinions and define the emotional impact of an organization / brand / product.
There is a 4-step-procedure to Successfully Predict Sentiment
Step 1. Retrieving data. Processing millions of mentions published on the Web and on Social Media, we collect the data required according to the needs of each individual customer
Step 2. Creating a customer data set – model training. Our team of analysts reads, annotates and classifies negative, positive or neutral mentions to each customer. In other words, they perform the initial model training and/or model evaluation for a plethora of of-the-shelf
models we maintain. The process is repeated on a monthly and or daily basis, depending on the needs and particularities of each project. In any case, the statistical sample of mentions manually annotated by our analysts does not exceed 20% of total mentions to the client.
Step 3. Create and test multiple models. Our Data Scientists create and test multiple models of sentiment prediction. Indicatively, our tests include:
- 7000 basic machine learning models. 3 basic algorithms, about 50 parameters per algorithm, and 48 variations in input data
- 600 deep learning models. 3 basic architectures, in four variants each, and 48 variants in the input data
- 90 sentiment analysis generic models also automatically adjusting them to the data of the individual customer
Step 4. Combination of models. Out of these approximately 7,690 models, we do not just choose the best: We combine them together, creating Ensemble Model for the best performance by channel (Twitter, Facebook, Instagram, YouTube, News, Blogs, Forums)