Automated text analysis in psychology: methods, applications, and future developments

Iliev, Rumen; Dehghani, Morteza; Sagi, Eyal

doi:10.1017/langcog.2014.30

Cited by 113 publications

(124 citation statements)

References 85 publications

Supporting

Mentioning

119

Contrasting

Unclassified

Order By: Relevance

“…37 A user-defined dictionary approach was adopted for its simplicity and cost-effectiveness over supervised machine learning. 36,38 The user-defined dictionary, created in WordStat, was used for a bottomup approach to the qualitative analysis and arranged in categories for the quantification. The combination of qualitative and quantitative approaches enhances the study of relatively complex processes of communication.…”

Section: Computer-assisted Content Analysis Of Newspapersmentioning

confidence: 99%

Scientific and non-scientific information in the uptake of health information: The case of Ebola

Falade¹,

Coultas²

2017

S. Afr. J. Sci.

View full text Add to dashboard Cite

The Ebola virus disease outbreak in West Africa (2013–2016) claimed over 10 000 lives in less than 18 months. Low levels of familiarity with the disease, ease of transmission, scale of infection, gruesomeness of symptoms, lack of cure and high fatality rate created a global panic. From the perspective of the social psychology of communication and content analysis, this study examines media coverage of the crisis in Africa with a view to unpacking the scientific and non-scientific information that may have framed public understanding of the disease. Findings show that accepting scientific advice was not unproblematic, because of the similarity of early symptoms with known diseases such as Lassa, dengue and malaria fevers. Cultural and religious actors and beliefs posed a paradox for believers as the public assimilated disease prevention information into existing norms and practices. Rumours and conspiracy theories about Western governments and pharmaceuticals also contributed to the rejection of the scientific explanation of its origin. Fear of the devastating effects of the disease and the lack of a cure led to the stigmatisation of the infected and treatment centres and ultimately to public revolts. Findings show the importance of non-scientific information and actors in matters of health and illness in Africa.

show abstract

Section: Computer-assisted Content Analysis Of Newspapersmentioning

confidence: 99%

Scientific and non-scientific information in the uptake of health information: The case of Ebola

Falade¹,

Coultas²

2017

S. Afr. J. Sci.

View full text Add to dashboard Cite

show abstract

“…As asserted by Iliev, Dehghani, and Sagi (2014), the constant increase of computational power and the wide availability of textual data will inevitably make automated text analysis a standard tool for researchers and psychologists.…”

Section: Resultsmentioning

confidence: 99%

Correlating Writer’s Block and Esl Learners’ Writing Quality

Rosa¹,

Genuino²

2018

Indonesian J. Appl. Linguist

View full text Add to dashboard Cite

Despite the importance of writing in the language learners' development, there are difficulties faced by English as a Second Language (ESL) learners that stem from various factors. One of them is the presence of writer's block that could affect writing quality. Therefore, this study aims to describe writer's block, along with a statistically-laden analysis of the possible correlation between the blocking experiences of 55 Filipino ESL learners and the levels of easability and readability of the essays they had written. This research employed a descriptive-correlational design using The Questionnaire in Identifying Writer's Block (QIWB) to gauge the extent of occurrence of writer's block and the Coh-Metrix Common Core Text Easability and Readability Assessor (hereafter CohMetrix T.E.R.A.), an online computational tool, to measure the levels of easability and readability of the essays. The result shows that the learners generally experienced writer's block, and their essays collectively showed high levels of easability on the basis of narrativity, referential cohesion, and deep cohesion. However, the essays were low in syntactic simplicity and word concreteness, while the level of readability computed exceeded that of the reading ability of 10 th -grade learners. Test of correlation revealed that there exists negligible relationship between writer's block and the overall easability and readability levels of the essays, though a significant but a weak relationship was documented between lateness and word concreteness and with premature editing and deep cohesion, respectively.Keywords: writer's block; easability; readability; text quality; Coh-Metrix T.E.R.A.When students are asked to write down on paper their thoughts about several concepts, or when the language teacher finally announces that an essay test will be administered, sighs of agony and apprehension reverberate in the L2 (second language) classroom. This situation is particularly prevalent among L2 learners whose writing performance is encumbered by a number of L2 writing issues such as the influence of the writer's personal characteristics, L2 writers' attitudes and composing processes, not to mention the interplay of cultural, social, political, and institutional contexts with L2 writing (Lee & Ferris, 2017). As such, the complexity of writing, as part of second language learning, continues to pose challenges to learners of different linguistic backgrounds and academic levels. Jun (2008) therefore asserts that the area of L2 writing qualifies relevant topics for second language researchers because of the many blank spots that could be filled in through languagerelated investigations.Aside from studies that highlight significant fields such as L2 writing feedback, L2 writing instruction, and L2 writers' texts, scholarly efforts to improve L2 writing learning and instruction also drifted to the area of writing process per se. Saadat and Dastgerdi (2014) describe research expanse in L2 writing as highlighted with studies that examine the effect of ...

show abstract

“…Statistically speaking, the ways in which words are used within a language are not randomly distributed (Iliev, Dehghani, & Sagi, 2014). Instead, the distribution of contextual words is predictable and defines its meaning.…”

Section: Statistical Semantics: Word Pattern Analysesmentioning

confidence: 99%

“…For example, the rows of the frequency matrix contain the words in a language, the columns contain word contexts and the cells contain the co-occurrence counts/frequency. The dimension reduction method used for LSA is referred to as singular value decomposition (Golub & Kahan, 1965;Landauer & Dumais, 1997) and is akin to principal component analysis (Iliev et al, 2014). The factors are typically referred to as dimensions and around 300 to 800 dimensions are usually extracted.…”

Section: Statistical Semantics: Word Pattern Analysesmentioning

confidence: 99%

Conceptualizing and Measuring Well-Being Using Statistical Semantics and Numerical Rating Scales

Kjell¹

2018

Preprint

View full text Add to dashboard Cite

How to define and measure individuals’ well-being is important, as this has an impact on both research and society at large. This thesis concerns how to define and measure the self-reported well-being of individuals, which involves both theorizing as well as developing and applying empirical and statistical methods in order to gain a better understanding of well-being.The first paper critically reviews the literature on well-being. It identifies an individualistic bias in current approaches and accompanying measures related to well-being and happiness; for example, through an over-emphasis on the importance of self-centered aspects of well-being (e.g., the unprecedented focus on satisfaction with life) whilst disregarding the importance of harmony in life, interconnectedness and psychological balance in relation to well- being. It is also discussed how closed-ended well-being measures impose the researchers’ values and limit the ability of respondents to express themselves in regard to their perceived well-being.The second paper addresses concerns regarding this individualistic bias by developing the harmony in life scale, which focuses on interconnectedness and psychological balance. In addition, an open-ended approach is developed in the paper, allowing individuals to freely describe their pursuit of well-being by means of open-ended responses analyzed using statistical semantics (including techniques from artificial intelligence such as natural language processing and machine learning). The results show that the harmony in life scale and the traditional satisfaction with life scale form a two-factor model of well-being, where the harmony in life scale explains more unique variance in measures of psychological well-being, stress, depression and anxiety, but not happiness. It is further demonstrated that participants describe their pursuit of harmony in life using words related to interconnectedness (including words such as: peace, balance, cooperation), whereas they describe their pursuit of satisfaction with life using words related to independence (including words such as: money, achievement, fulfillment). It is concluded that the harmony in life scale complements the satisfaction with life scale for a more comprehensive understanding of subjective well-being.The third paper focuses on developing and evaluating a method for measuring and describing psychological constructs using open-ended questions analyzed by means of statistical semantics rather than closed-ended numerical rating scales. This semantic measures approach is tested and compared with traditional rating scales in nine studies, including two different paradigms involving reports regarding objective stimuli (i.e., the evaluation of facial expressions) and reports regarding subjective states (i.e., the self-reporting of harmony in life, satisfaction with life, depression and worry). The results indicate that semantic measures encompass higher, or competitive, levels of reliability and validity compared to traditional numerical rating scales. In addition, semantic measures appear to be better suited for differentiating between psychological constructs, such as harmony in life versus satisfaction with life as well as depression versus worry.In this thesis, the findings from these three papers are elaborated and integrated into two independent perspectives. The first perspective focuses on the theoretical and empirical differences between harmony in life and satisfaction with life within a context of societal and national progress. It is concluded that harmony in life complements satisfaction with life. The second perspective focuses on the open-ended, statistical semantics approach. It is proposed that statistical semantics may beneficially be used more widely as a research tool within psychological research.

show abstract

Automated text analysis in psychology: methods, applications, and future developments

Cited by 113 publications

References 85 publications

Scientific and non-scientific information in the uptake of health information: The case of Ebola

Scientific and non-scientific information in the uptake of health information: The case of Ebola

Correlating Writer’s Block and Esl Learners’ Writing Quality

Conceptualizing and Measuring Well-Being Using Statistical Semantics and Numerical Rating Scales

Contact Info

Product

Resources

About