• Kushagra Seth
• Sahil Singh Patwal
• Dr. Amita Misra
• Dr. Amita Goel

We can frequently identify from an individual's articulations whether he/she is in support or against a given target element (an item, topic, person, and so on.). Here, we present a dataset of tweets where the tweeter is in support or against pre-picked targets of intrigue—their stance/opinion. The objectives of intrigue might be alluded to in the tweets, and they could conceivably be the objective of feeling in the tweets. The information relates to tweets about environmental change and a worldwide temperature alteration usually known and debated in the United States. The main aim of stance classification/opinion analysis is to automatically detect the stance of the author from the tweet expressed towards a particular target, which is an emerging issue in sentiment analysis. A noteworthy contrast between stance classification and sentiment analyzation is that stance is reliant on target which probably won't be unequivocally referenced in the tweet. This shows aside from the content of the tweet; the target data is critical to stance detection. Therefore, we propose a neural network-based system, which fuses target-specific data into stance detection. It remains a challenge to develop a tweet's vector representation w.r.t the target, particularly when the target is just implicitly referenced, or not referenced at all in the text. This is why target information is incorporated into tweet's vector representation by using pre-trained word embeddings. This was a venture to build up a vigorous arrangement model which can distinguish the stance/opinion of a tweeter and likewise group him into its right class, i.e., either support or against the given target substance. We chose the model which produced the most remarkable precision/accuracy on the climate change dataset.

Stance Classification, word embeddings, neural network, tweet, climate change

"CLIMATE CHANGE STANCE CLASSIFICATION using Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), RNN-LSTM & CNN-LSTM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 5, page no.35-46, May-2019, Available :http://www.jetir.org/papers/JETIR1905A04.pdf

"CLIMATE CHANGE STANCE CLASSIFICATION using Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), RNN-LSTM & CNN-LSTM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 5, page no. pp35-46, May-2019, Available at : http://www.jetir.org/papers/JETIR1905A04.pdf