search

cbaziotis / datastories-semeval2017-task4

Deep-learning model presented in "DataStories at SemEval-2017 Task 4: Deep LSTM with Attention for Message-level and Topic-based Sentiment Analysis".
MIT License
196 stars 63 forks source link

what is 'input_aspect' #35

Open bayou3 opened 6 years ago

bayou3 commented 6 years ago

Hi Can I ask that what is input_aspect ? Is the aspect like query terms? If so , then what is training[1] in 'history = nn_model.fit(training[0], training[1]' of model_target.py ?

cbaziotis commented 6 years ago

input_aspect refers to the words of the topic (aspect). In the target based tasks (B, C, D, E) we have to estimate the sentiment polarity of a tweet with respect to a given topic, which may be one or more words.

It corresponds to the topic input in the following figure (same thing - different name). MSA