LITERACY SERVEY ON SENTIMENTAL ANALYSIS

CHAPTER 2

“As people increasingly use emoticons in text in order to express, stress, or disambiguate their
sentiment, it is crucial for automated sentiment analysis tools to correctly account for such
graphical cues for sentiment. We analyze how emoticons typically convey sentiment and
demonstrate how we can exploit this by using a novel, manually created emoticon sentiment
lexicon in order to improve a state-of-the-art lexicon-based sentiment classification method. We
evaluate our approach on 2,080 Dutch tweets and forum messages, which all contain emoticons
and have been manually annotated for sentiment. On this corpus, paragraph-level accounting for
sentiment implied by emoticons significantly improves sentiment classification accuracy. This
indicates that whenever emoticons are used, their associated sentiment dominates the sentiment
conveyed by textual cues and forms a good proxy for intended sentiment.”
-DANIELLA BAL, MALISSA BAL, UZAY KAYMAK
(Erasmus University Rotterdam, Netherlands - MARCH 2013)

“Efthymios Kouloumpis, TheresaWilson, Johns Hopkins University, USA,Johanna Moore,

School of Informatics University of Edinburgh, Edinburgh,UK in a paper on Twitter Sentiment
Analysis:The Good the Bad and theOMG! in July 2011 have investigate the utility of linguistic
features fordetecting the sentiment of Twitter messages. We evaluate the usefulness ofexisting
lexical resources as well as features that capture information aboutthe informal and creative
language used in microblogging. We take asupervised approach to the problem, but leverage
existing hashtags in theTwitter data for building training data.”

-EFTHYMIOS KOULOMPIS, THERESA WILSON

“Hassan Saif, Yulan He and Harith Alani, Knowledge Media Institute, TheOpen University,
United Kingdom in a paper Semantic Sentiment Analysisof Twitter in Nov 2012 they have
introduce a novel approach of addingsemantics as additional features into the training set for
sentiment analysis.For each extracted entity (e.g. iPhone) from tweets, we add its
semanticconcept (e.g. “Apple product”) as an additional feature, and measure thecorrelation of
the representative concept with negative/positive sentiment.”

- HASSAN SAIF, HARITH ALANI

“Subhabrata Mukherjee1, Akshat Malu1, Balamurali A.R.12, PushpakBhattacharyya1,1Dept. of
Computer Science and Engineering, IIT Bombay,2IITB-Monash Research Academy, IIT
Bombay on a paper on TwiSent: AMultistage System for Analyzing Sentiment in Twitter in Feb
2013 theyhave presented TwiSent, a sentiment analysis system for Twitter. Based on thetopic
searched, TwiSent collects tweets pertaining to it and categorizes theminto the different polarity
classes positive, negative and objective. However,analyzing micro-blog posts have many
inherent challenges compared to theother text genres.”

-SUBHABRATA MUKHERJEE, AKSHAT MALU,BALAMURALI

“Isaac G. Councill, Ryan McDonald, Leonid Velikovich, Google, Inc., NewYork on a paper on
What’s Great and What’s Not: Learning to Classify theScope of Negation for Improved
Sentiment Analysis in July 2010 presentsa negation detection system based on a conditional
random field modelledusing features from an English dependency parser. The scope of
negationdetection is limited to explicit rather than implied negations within
singlesentences. LITERATURE SURVEY”

-ISSAC G, RYAN MCDONALD, LEONID VELIKOVICH

“In this article we report on ethnographic research that explores the range of ways in which
Spanish‐English bilingual immigrant youth interpret English language texts for their families.
Drawing on participant observation in the homes and classrooms of 18 young adolescents who
serve as interpreters for their families, 86 transcripts of the seinterpreters' oral Spanish
translations of English texts, and 95 journal entries written by the youth about their translating
experiences, we document the multiple literacies of daily life that youth engage in while
translating or “para‐phrasing” for their families. We focus on interpretations of written text for
close family members, done at home, and chart the domains of these multiple literacies. Using an
activity setting/interactional analysis, we then examine how two home “para‐phrasing” events
unfold and contrast these with activity settings for literacy learning in school. This largely
unexplored literacy practice is a common one in immigrant households, and we argue that
bilingual youth's experiences as cross‐language “para‐phrasers” can be used to support the
within‐language paraphrasing that is an important part of school literacy practices.”

-JENNIFER REYNOLDS, LISA DORNER, MARIA MEZA

(Northwestern University, USA – NOVEMBER 2011)

“BACKGROUND: Many older adults in Medicare managed care programs have low health
literacy, and this may affect use of preventive services.

OBJECTIVE: To determine whether older adults with inadequate health literacy were less

likely to report receiving influenza and pneumococcal vaccinations, mammograms, and
Papanicolaou smears than individuals with adequate health literacy after adjusting for other
covariates. MEASERS: Short Test of Functional Health Literacy in Adults and self-reported
preventive service use.

RESULT: After adjusting for demographics, years of school completed, income, number of
physician visits, and health status, people with inadequate health literacy were more likely to
report they had never received the influenza (OR, 1.4; 95% CI, 1.1–1.9) or pneumococcal
vaccination (OR, 1.3; 95% CI, 1.1–1.7), and women were less likely to have received a
mammogram (OR, 1.5; 95% CI, 1.0–2.2) or Papanicolaou smear (OR, 1.7; 95% CI, 1.0–3.1).

CONCLUSION: Among Medicare managed care enrollees, inadequate health literacy is

independently associated with lower use of preventive health services.”

-SCOTT, TRACY L, JULIE A, DAVID

( Emory University School of Medicine, Georgia.)

 “They worked on Financial literacy (or financial knowledge) which is typically an input to
model the need for financial education and explain variation in financial outcomes. Defining and
appropriately measuring financial literacy is essential to understand educational impact as well as
barriers to effective financial choice. This article summarizes the broad range of financial
literacy measures used in research over the last decade. An overview of the meaning and
measurement of financial literacy is presented to highlight current limitations and assist
researchers in establishing standardized, commonly accepted financial literacy instruments.”

-SANDRA J.HUSTON

(ASSOCIATE PROFESSOR OF PERSONAL

FINANCIAL PLANNING FROM TEXAS UNIVERSITY, JUNE 2010)
“They worked on The National Adult Literacy Survey profiled the literacy of U.S. adults based
on their performance on tasks reflecting materials and demands of daily life. Data were gathered
through interviews with a random sample of 13,600 people over 16, a survey of 1,000 adults in
each of 12 states, and interviews with 1,100 prison inmates, making a total of 26,000 adults
surveyed. Participants completed a series of literacy tasks and received proficiency scores on
three scales measuring prose, document, and quantitative literacy. They were categorized in five
levels. Major findings were as follows: (1) 40-44 million adults were at the lowest level, of
whom 25% were immigrants, 62% did not complete high school, and 19% had visual difficulties;
(2) 50 million at level 2 had difficulty with higher reading and problem-solving skills; (3) most at
levels 1-2 rated their reading/writing as well or very well--they could meet most needs with
limited skills; (4) 61 million were at level 3, 34-40 million at levels 4-5; (5) young adults were
less proficient than those surveyed in 1985; (6) older adults were more likely to have limited
skills; (7) many minorities and prison inmates were more likely to be at levels 1-2, due to fewer
years of schooling or limited English proficiency; (8) higher levels correlated with being
employed, working more weeks, and having higher wages; and (9) 41-44% of level 1 and 4-8%
of levels 4-5 were in poverty. (Appendices include definitions and 31 data tables. Document
includes 13 other tables and 26 figures.)”

-KIRSCH, IRWIN S

“They worked on Publicly funded prekindergarten programs have achieved small‐to‐large

impacts on children's cognitive outcomes. The current study examined the impact of a
prekindergarten program that implemented a coaching system and consistent literacy, language,
and mathematics curricula on these and other nontargeted, essential components of school
readiness, such as executive functioning. Participants included 2,018 four and five‐year‐old
children. Findings indicated that the program had moderate‐to‐large impacts on children's
language, literacy, numeracy and mathematics skills, and small impacts on children's executive
functioning and a measure of emotion recognition. Some impacts were considerably larger for
some subgroups. For urban public school districts, results inform important programmatic
decisions. For policy makers, results confirm that prekindergarten programs can improve
educationally vital outcomes for children in meaningful, important ways.”

-CHRISTINA WEILAND, HIROKAZU YOSHIKAWA

(PROFESSORS AT HARVARD GRADUATE SCHOOL-2013)

“They worked on the research explores literacy teachers’ perceptions of integrating information
communication technologies (ICTs) into literacy instruction. To this end, a national survey of
1,441 literacy teachers in the United States was conducted. The survey provided data concerning
the types and levels of reported availability and use of ICTs, beliefs about the importance of
integrating ICTs into literacy instruction, and perceived obstacles to doing so. The analysis of
data included descriptive statistics, an exploratory factor analysis, and a path analysis used to test
a model hypothesizing a relation between teachers’ perceived importance of technology and
reported levels of integration. Results revealed relatively low levels of curricular integration,
consistent perceptions about obstacles to integration, and technological rather than curricular
definitions of ICTs and of integration. The path analysis suggested several characteristics and
influences associated with higher levels of integration and use. The findings advance
understanding of the extent to which ICTs are being integrated into literacy instruction and what
factors should be considered toward profitably increasing integration consistent with expanding
definitions of literacy.”

-AMY HUTCHISON, DAVID REINKING

(Clemson university, South Carolina, USA-2011)