Using language models to improve opinion detection

Abstract

A B S T R A C T :Opinion mining is one of the most important research tasks in the information retrieval research community. With the huge volume of opinionated data available on the Web, approaches must be developed to differentiate opinion from fact. In this paper, we present a lexicon-based approach for opinion retrieval. Generally, opinion retrieval consists of two stages: relevance to the query and opinion detection. In our work, we focus on the second state which itself focusses on de-tecting opinionated documents . We compare the document to be analyzed with opinionated sources that contain subjective information. We hypothesize that a document with a strong si-milarity to opinionated sources is more likely to be opinionated itself. Typical lexicon-based approaches treat and choose their opinion sources according to their test collection, then cal-culate the opinion score based on the frequency of subjective terms in the document. In our work, we use different open opinion collections without any specific treatment and consider them as a reference collection. We then use language models to determine opinion scores. The analysis document and reference collection are represented by different language models (i.e., Dirichlet, Jelinek-Mercer and two-stage models). These language models are generally used in information retrieval to represent the relationship between documents and queries. However, in our study, we modify these language models to represent opinionated documents. We carry out several ex-periments using Text REtrieval Conference (TREC) Blogs 06 as our analysis collection and Internet Movie Data Bases (IMDB), Multi-Perspective Question Answering (MPQA) and CHESLY as our reference collection. To improve opinion detection, we study the impact of using different language models to represent the document and reference collection alongside different com-binations of opinion and retrieval scores. We then use this data to deduce the best opinion de-tection models. Using the best models, our approach improves on the best baseline of TREC Blog (baseline4) by 30%.

Performance prediction of multivariable linear regression based on the optimal influencing factors for ranking aggregation in crowdsourcing task

“…In order to verify the effectiveness of the proposed method, a comparison is made from two aspects. On the one hand, in order to well reflect the wisdom of crowd wisdom, the aggregated results were compared with the state-of-the-art blog opinion finding algorithm (Belbachir and Boughanem, 2018;Huang et al, 2018). On the other hand, the set of optimal influencing factors were compared with other sets of influencing factors proposed by Wu and Mcclean (2006); Xing et al (2015), respectively.…”

“…The first comparative method was proposed by Belbachir and Boughanem (2018). Their test task was 50 queries from TREC Blog Opinion 2006.…”

Sentiment analysis on massive open online course evaluations: A text mining and deep learning approach

“…In the summarization module, user's query relevant sentences have been identified. Belbachir and Boughanem [10] utilized language models used in information retrieval to represent the query and document for sentiment analysis. Moreover, Al-Smadi et al [8] employed morphological, syntactic, and semantic features for sentiment analysis.…”

The evolution of argumentation mining: From models to social media and emerging tools

“…Opinion mining and sentiment analysis could be characterized as the predecessors of AM in a simplified form and their limits have already been questioned in the effort for seeking a deeper understanding of the human reasoning [10,11]. As AM we define a series of actions that could be independent or connected to each other and they are relevant to the tasks of detection, extraction and evaluation of arguments, where argument is a piece of text offering evidence or reasoning in favor or against a specific topic.…”