Extracting Product Features and Opinions from Reviews - Natural Language Processing and Text Mining - page 22

Table 2.9. Finding Word Semantic Orientation Labels in the Context of
Given Features and Sentences. opine's precision is higher than that of PMI++
and Hu++ . All results are reported with respect to PMI++ .

Word POS PMI++ Hu++ OPINE

Precision Recall Precision Recall Precision Recall

Adjectives 0.73 0.91 +0.02 -0.17 +0.07 -0.03

Nouns 0.63 0.92 +0.04 -0.24 +0.11 -0.08

Verbs 0.71 0.88 +0.03 -0.12 +0.01 -0.01

Adverbs 0.82 0.92 +0.02 -0.01 +0.06 +0.01

Avg 0.72 0.91 +0.03 -0.14 +0.06 -0.03

Table 2.10. Extracting Opinion Phrases and Opinion Phrase Polarity
in the Context of Known Features and Sentences. opine's precision is
higher than that of PMI++ and Hu++ . All results are reported with respect
to PMI++ .
Measure PMI++ Hu++ OPINE

Opinion Extraction: Precision 0.71 +0.06 +0.08

Opinion Extraction: Recall 0.78 -0.08 -0.02

Opinion Polarity: Precision 0.80 -0.04 +0.06

Opinion Polarity: Recall 0.93 +0.07 -0.04

and Hu++ is mostly due to its ability to handle context-sensitive words in
a large number of cases.
Although Hu++ does not handle context-sensitive SO label assignment,
its average precision was reasonable (75%) and better than that of PMI++ .
Finding a word's SO label is good enough in the case of strongly positive or
negative opinion words, which account for the majority of opinion instances.
The method's loss in recall is due to not recognizing words absent from Word-
Net ( e.g. , “depth-adjustable”) or not having enough information to classify
some words in WordNet.
PMI++ typically does well in the presence of strongly positive or strongly
negative words. Its main shortcoming is misclassifying terms such as “basic”
or “visible” which change orientation based on context.

Experiments: Opinion Phrases

In order to evaluate opine on the tasks of opinion phrase extraction and
opinion phrase polarity extraction in the context of known features and sen-
tences, we used a set of 550 sentences containing previously extracted features.
The sentences were annotated with the opinion phrases corresponding to the
known features and with the opinion polarity. The task of opinion phrase po-
larity extraction differs from the task of word SO label assignment above as
follows: the polarity extraction for opinion phrases only examines the assign-