Sentiment Analysis

Package connectcontactlens provides the API client, operations, and parameter types for Amazon Connect Contact Lens. Contact Lens actions Contact Lens data types Amazon Connect Contact Lens enables you to analyze conversations between customer and agents, by using speech transcription, natural language processing, and intelligent search capabilities. It performs sentiment analysis, detects issues, and enables you to automatically categorize contacts. Amazon Connect Contact Lens provides both real-time and post-call analytics of customer-agent conversations. For more information, see Analyze conversations using speech analyticsin the Amazon Connect Administrator Guide.

Package govader implements the vader sentiment analysis algorithm see https://github.com/cjhutto/vaderSentiment

Package golinear trains and applies linear classifiers. The package is a binding against liblinear with a Go-ish interface. Trained models can be saved to and loaded from disk, to avoid the (potentially) costly training process. A model is trained using a problem. A problem consists of training instances, where each training instance has a class label and a feature vector. The training procedure attempts to find one or more functions that separate the instances of two classes. This model can then predict the class of unseen instances. Consider for instance that we would like to do sentiment analysis, using the following, humble, training corpus: To represent this as a problem, we have to convert the classses (positive/negative) to an integral class labels and extract features. In this case, we can simply label the classes as positive: 0, negative: 1. We will use the words as our features (a: 1, beautiful: 2, album: 3, crappy: 4, ugly: 5) and use booleans as our feature values. In other words, the sentences will have the following feature vectors: We can now construct the problem using this representation: The problem is used to train a linear classifier using a set of parameters to choose the type of solver, constraint violation cost, etc. We will use the default parameters, which train a L2-regularized L2-loss support vector classifier. Of course, now we would like to use this model to classify other sentences. For instance: We map this sentence to the feature vector that we used during training, simply ignoring words that we did not encounter while training the model: The Predict method of the model is used to predict the label of this feature vector. As expected, the model will predict the sentence to be positive (0).

Package golinear trains and applies linear classifiers. The package is a binding against liblinear with a Go-ish interface. Trained models can be saved to and loaded from disk, to avoid the (potentially) costly training process. A model is trained using a problem. A problem consists of training instances, where each training instance has a class label and a feature vector. The training procedure attempts to find one or more functions that separate the instances of two classes. This model can then predict the class of unseen instances. Consider for instance that we would like to do sentiment analysis, using the following, humble, training corpus: To represent this as a problem, we have to convert the classses (positive/negative) to an integral class labels and extract features. In this case, we can simply label the classes as positive: 0, negative: 1. We will use the words as our features (a: 1, beautiful: 2, album: 3, crappy: 4, ugly: 5) and use booleans as our feature values. In other words, the sentences will have the following feature vectors: We can now construct the problem using this representation: The problem is used to train a linear classifier using a set of parameters to choose the type of solver, constraint violation cost, etc. We will use the default parameters, which train a L2-regularized L2-loss support vector classifier. Of course, now we would like to use this model to classify other sentences. For instance: We map this sentence to the feature vector that we used during training, simply ignoring words that we did not encounter while training the model: The Predict method of the model is used to predict the label of this feature vector. As expected, the model will predict the sentence to be positive (0).

Package golinear trains and applies linear classifiers. The package is a binding against liblinear with a Go-ish interface. Trained models can be saved to and loaded from disk, to avoid the (potentially) costly training process. A model is trained using a problem. A problem consists of training instances, where each training instance has a class label and a feature vector. The training procedure attempts to find one or more functions that separate the instances of two classes. This model can then predict the class of unseen instances. Consider for instance that we would like to do sentiment analysis, using the following, humble, training corpus: To represent this as a problem, we have to convert the classses (positive/negative) to an integral class labels and extract features. In this case, we can simply label the classes as positive: 0, negative: 1. We will use the words as our features (a: 1, beautiful: 2, album: 3, crappy: 4, ugly: 5) and use booleans as our feature values. In other words, the sentences will have the following feature vectors: We can now construct the problem using this representation: The problem is used to train a linear classifier using a set of parameters to choose the type of solver, constraint violation cost, etc. We will use the default parameters, which train a L2-regularized L2-loss support vector classifier. Of course, now we would like to use this model to classify other sentences. For instance: We map this sentence to the feature vector that we used during training, simply ignoring words that we did not encounter while training the model: The Predict method of the model is used to predict the label of this feature vector. As expected, the model will predict the sentence to be positive (0).

Package provides easy integration with AWS Comprehend APIs Amazon Comprehend is a platform within Amazon Web Services (AWS) that uses machine learning to find insights in unstructured text. You can either use pre-trained text analysis models or customize your own to extract specific pieces of information, identify sentiment, and find topics in a collection of documents.

Package gobay implements Naive Bayesian Classifier for sentiment analysis.

Before running this program, first fetch the data with fetch-all-questions into some base directory. Pass this base directory with the -dir flag to this program. To get a month-by-month breakdown from start date to end date, use the -bymonth flag. Eli Bendersky [https://eli.thegreenplace.net] This code is in the public domain. StackOverflow analysis using its API in Go. This program just fetches data from the StackOverflow API. The idea is that you run it once to fetch all the data you need, and can then analyze this data locally by repeatedly invoking analyze-question-sentiment with different parameters. To get the increased API quota, get a key from stackapps.com and run with the env var STACK_KEY=<key> Eli Bendersky [https://eli.thegreenplace.net] This code is in the public domain.

Package govader implements the vader sentiment analysis algorithm see https://github.com/cjhutto/vaderSentiment