Enter your API key here and click on Submit. A pop-up message would confirm if your API key has been successfully submitted. You can start your analysis now.
ParallelDots APIs are present in the form of Excel Functions to be directly used to analyze any type of Unstructured Textual Content.
Function Name : paralleldots_sentiment
Using the function paralleldots_sentiment you can analyze any textual content and in return get the sentiment attached to the text.
Consider the following example where the text sentence “These brownies are the worst in the world.” is being analyzed using paralleldots_sentiment.
Functions paralleldots_sentiment_negative_probability, paralleldots_sentiment_neutral_probability, paralleldots_sentiment_positive_probability give the probability score between 0 to 1 for each sentiment label (Negative, Neutral and Positive). The sentiment with the highest probability score is the overall Sentiment of the text content.
Sentiment Analysis can also be done in different languages namely Spanish, Portuguese and Chinese. It works the same way as our Sentiment Analysis works.Spanish
Function Name : paralleldots_multilang_es
Function Name : paralleldots_multilang_pt
Function Name : paralleldots_multilang_cn
In the functions es, pt and cn are the language codes for Spanish, Portuguese and Chinese respectively. The only difference in using sentiment analysis and multilingual sentiment analysis is that now you get the confidence score as your probability. To get the confidence score you can add _confidence in each of the functions like “paralleldots_multilang_es_confidence” will get you the confidence score of the Spanish sentence that you give as input. It varies between 0 and 1, the closer the number is to 1, as accurate is the analysis.
Consider the following example where Barcelona, Lima and Beijing are praised for being beautiful in their native languages.
Function Name : paralleldots_keywords
Keyword Generator API is a powerful tool in text analysis that is used to index data, generate tag clouds and accelerate the searching time. Using the function paralleldots_keywords you can generate an extensive list of relevant keywords and phrases to make research more context based.
Consider the following example where keywords are generated in the following sentence “For the Yankees, it took a stunning comeback after being down 2-0 to the Indians in the American League Division Series.”
Function Name : paralleldots_taxonomy
Text Classification is a very powerful tool in understanding customer behavior by categorizing data sets on a large scale. You can assign categories to a text content using the paralleldots_taxonomy function, allowing to structure data for better insights.
Consider the following example where text input “AN OUTBREAK of pneumonic plague - commonly known as the Black Death - has killed at least 45 people and could become an epidemic.” are assigned the relevant categories using the Text Classification API.
Function Name : paralleldots_ner
Entity Extraction is a very powerful tool and can identify individuals, companies, places organization, cities and other various type of entities. This is broken into three categories namely Person, Organization and place which can be called using functions pralleldots_ner_person, paralleldots_ner_organization and paralleldots_ner_place respectively
Please note in order to use the Entity Extraction API you must be giving the relevant type along with the function. (person, organization and place).
Consider the following text input “When Michael Jordan was at the peak of his powers as an NBA superstar, his Chicago Bulls teams were mowing down the competition, winning six National Basketball Association titles and setting a record for wins in a season that was broken by the Golden State Warriors two seasons ago.” where entities are extracted using paralleldots_ner_person, paralleldots_ner_organization and paralleldots_ner_place respectively.
Function Name : paralleldots_similarity
Semantic analysis API helps users cluster similar articles by understanding relatedness between different textual content and streamlines research by eliminating redundant text contents. Using semantic analysis (similarity) API function, paralleldots_similarity, you give two text inputs as parameters to compare and get a relatedness score out of 5. A score between 0-2.5 shows low similarity, 2.5 to 3.5 shows mild correlation and a score between 3.5 to 5 shows strong similarity.
Consider the following example where two sentences are being compared “Michael Jordan is the best player in the world” and “Lionel Messi is the best player in the world”.
Function Name : paralleldots_emotion
Sometimes the three classes of sentiment (positive, negative and neutral) are not sufficient to understand the nuances regarding the underlying tone of a sentence. Our Emotion Analysis classifier is trained on our proprietary dataset and tells whether the underlying emotion behind a message is: Happy, Sad, Angry, Excited, or Indifferent(Other). You can use the paralleldots_emotion function to find out the emotion in any text content.
Also, you can find out the probability related to each of the underlying emotion. Use paralleldots_emotion_ <label>_probabilty to get the probability of each emotion. You can use happy, sad, angry, excited or other in place of <label>. For eg paralleldots_emotion_happy_probability will return the probability of happy emotion on the text given as input.
Consider the following eg. where the text input “The latest Porcupine Tree song is rocking!” is being categorized using emotion detection API.
Function Name : paralleldots_intent
This intent analysis classifier tells whether the underlying intention behind a sentence is feedback/opinion, news, query, spam or other. You can find the intent behind any text content using the paralleldots_intent function.
Also, you can find the probability related to each of the underlying intent. Use paralleldots_intent_<label>_probabilty to get the probability of each intent. You can use feedback_opinion, news, query, spam or other in place of <label>. For eg: paralleldots_intent_feedback_opinion_probability will return the probability of feedback_opinion intent on the text given as input.
Consider the following example where the text input "Michael Jordan on NBA parity: 28 teams 'are going to be garbage'" is being categorized using intent analysis API.
Function Name : paralleldots_abuse
The abusive content classifier API detects abuse and helps users filter abusive content. You can classify input text content as abusive or not using the paralledots_abuse function.
Also, you can get the confidence score i.e the probability using paralleldots_abuse_confidence between 0 to 1 to judge the accuracy of the result.
Consider the following the example where the text input "Is this content abusive?" is being classified as Abusive or not using our abusive content classifier API.
However, in some cases due to contractual obligations or otherwise, user may want to keep the data in-house in which case we can deploy these algorithms on premise and build the plugin accordingly. Please send us a request to deploy these APIs on premise and any custom function that you want us to build.
Please write to us at firstname.lastname@example.org in case of any queries or feedback.