Hatzivassiloglou and McKeown (1997) proposed an algorithm that uses syntactic cues. If two adjectives are frequent conjoined by “and” and rarely conjoined by “but”, they are considered similar. And if they’re more likely to be conjoined by “but”, they are likely to have opposite polarity. 

Syntactic Cues Based algorithm

Other methods find words with similar polarity using thesaurus such as WordNet. A word’s synonyms are assumed to have similar polarity, and a word’s antonyms are assumed to have opposite polarity.

Finding Words With Similar Polarity Using Thesaurus

The core of semisupervised algorithms of induction of affect lexicons lies in the metric of measuring seed word similarities. Besides embedding cosine, there’re other methods.

University of Notre Dame

This way of learning sentiment lexicons make use of two sets of seed words like good or bad which in turn will find out the similarity of a particular word to any of the two seed word sets.

There are two types of seed-based semi-supervised lexicon induction algorithms,

- Axis-based 

- Graph-based 

Semi-supervised Induction of Affect Lexicons

An on-going but a helpful book resource about NLP
https://web.stanford.edu/~jurafsky/slp3/

Speech and Language Processing (3rd ed. draft) 

Seed words like good or bad are given.

For a given word, ‘w’ to be labeled ,a measurement of how much each word 'w' is similar to the good word and different from the bad word is calculated.


Axis-based semi-supervised lexicon induction algorithms

Defining lexicons by propagating sentiment labels on graphs. SentProp (Sentiment Propagation) algorithm is developed on this idea.

Learn Before

Related

Learn After