Essay Sample on Depression and Mental Illnesses

Introduction

People with mental illness face stigma because of the way the society treats people with mental illness especially in Arabic countries. The stigma towards the people with mental illness occur in form of three categories: firstly there is beliefs toward a person with a mental illness by the society. Among the beliefs include religious and cultural beliefs as shame, blame, the person is crazy or has been punished by God. The second category people with mental illness are stigmatized include the attitudes of the people that they live with towards them. The attitude instil fear among the people with mental illness where they fear being addicted psychiatric medications and their side effects. The third category include the way the mental illness patients are treated based on the actions of the people in the society towards them. Some of the actions include being distanced by close family members such as partners [1].

Is your time best spent reading someone else’s essay? Get a 100% original essay FROM A CERTIFIED WRITER!

Order now

Depression can be characterized to be a disorder in the mood of the person where the patient keeps on having a constant feeling of loss of interest and sadness. The disorder affects the thinking, feeling and behavior of the patient. In addition, it may cause many other psychological and physical problems. The patient faces difficulties in doing normal daily activities since they feel that the live is not worth living hence no need of doing the activities [2]. The unipolar depression is among the main depressive disorder diagnosed in patients who have five or more of the symptoms described below for two weeks; among the major symptoms include loss of interest or depressed mood [3].

There are various symptoms of depression, they include loss of interest, change in appetite or weight, depressed mood, feelings of guilt and worthlessness, poor concentration, sleep disorder, fatigue or loss of energy, psychomotor agitation and the patient also contemplate suicide [2].

Several psychometric self-report surveys have been conducted among the patients with mental illnesses, among the surveys include the Epidemiologic Studies Depression Scale center (CES-D) and the Patient Health Questionnaire (PHQ-9), both surveys include questionnaire developed to ascertain the symptoms of depression among the population and they considered as a screening instrument in primary care clinics and in research. The PHQ-9 is a 9-item while the CES-D is a 20-item. Both have a minimum score is zero and a maximum score in the CES-D is 60. Unlike the PHQ-9 is 20. Generally, depression symptoms in those questionnaires are divided into levels based on the likelihood of having depression: mild, moderate, moderately severe and severe [2] [4].

Sentiment Analysis (Opinion Mining)

Sentiment analysis is the procedure of ascertaining the sentiment of text as neutral, negative or positive through the use of natural language processing (NLP) text analysis and machine learning [5]. Analysis of the Sentiment allows discovery of people' opinions towards different topics, products, education, services, events, issues etc. [6]. SA is concerned with supports an organization's decision-making process. The main Components of an opinion include [5]: Object is an opinion target while Aspect is an attribute, the Sentiment orientation is an opinion sentiment concerning the opinion and classifying it into either neutral, negative or positive. The opinion holder holds an opinion on a specific Opinion or object is the attitude, view, emotion or appraisal towards an object by the person who has the view concerning the object.

Several approaches have been proposed to sentiment analysis, some focusing on supervised, others on unsupervised. The supervised approach depends on corpus data with labels (positive /negative) to train a classifier (s) where the classifiers are algorithms of learning of the machine such as Artificial Neural Networks (ANN), Naive Bayes (NB), Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) [5][7]. On another hand, the unsupervised approach also called lexicon-based approach, a lexicon is building that contains words and their identical sentiments where the word is stored in lexicon with a score that appears its aspects such as negative or positive), in contrast, labels are not required [5][7].

Complexity in Arabic Sentiment Analysis

The Arabic language is primarily used as the main language in 27 states and a secondary language in many other countries, an estimate of 422 million people speak Arabic in their countries [5]. Arabic language is a Semitic language that consists main characteristics are 28 letters, including the vowels letters (a o y), an orientation of writing is from right to left, letters can be written with various shapes based on their position in the word and no upper or lower case for letters, unlike English letters [6][8][9].

The authors, in their paper [5][9], discuss the complexity of Arabic language, which includes the two most important points: Arabic orthography and Arabic morphology. The Arabic orthography, Naaima et al, indicate to most of the Modern Standard Arabic (MSA) texts are written without diacritical marks which caused a lexical ambiguity problem such as word (), which has three meanings. "" means poetry or "" means hair or "" means feel [5]. Morphological complexities, where the Arabic word has multiple morphological aspects: derivation and inflection, in derivational morphology is concerned with making new word using an existing word, which called "root". Researchers agree there is a need for Arabic analyzers of morphology that use the POS taggers in root extraction such as the extraction of suffix, prefix and affix. The analyzers of morphology were used in the formation of the Arabic language, they include MADA (the Morphological Analysis and Disambiguation for Arabic analyzer) and BAMA (the Buckwalter Arabic Morphological Analyzer). In inflectional morphology which indicates to grammatical categories: Arabic word can be a particle, verb or noun. The particles consist of words that don't come from the above mentioned classification.

Related Work

This section presents a review of prior studies related to depression prediction on a social media network. We summarized the main characteristics of seven studies in table 1, then we point out some of the advantages and limitations of existing methods.

Year Dataset Mental Illness Criteria Features Approach Performance Measures

Potential benefits of using online social network data for clinical studies on depression are tremendous. In this pa- per, we present a preliminary result on building a research framework that utilizes real-time moods of users captured in the Twitter social network and explore the use of language in describing depressive moods. First, we analyzed a ran- dom sample of tweets posted by the general Twitter popula- tion during a two-month period to explore how depression is talked about in Twitter. A large number of tweets contained detailed information about depressed feelings, status, as well as treatment history. Going forward, we conducted a study on 69 participants to determine whether the use of senti- ment words of depressed users differed from a typical user. We found that the use of words related to negative emo- tions and anger significantly increased among Twitter users with major depressive symptoms compared to those other- wise. However, no difference was found in the use of words related to positive emotions between the two groups. Our work provides several evidences that online social networks provide meaningful data for capturing depressive moods of users.

Twitter 69-participants

"Depression is a serious and widespread public health challenge. We examine the potential for leveraging social media postings as a new type of lens in understanding depression in populations. Information gleaned from social media bears potential to complement traditional survey techniques in its ability to provide finer grained measurements over time while radically expanding population sample sizes. We present work on using a crowdsourcing methodology to build a large corpus of postings on Twitter that have been shared by individuals diagnosed with clinical depression. Next, we develop a probabilistic model trained on this corpus to determine if posts could indicate depression. The model leverages signals of social activity, emotion, and language manifested on Twitter. Using the model, we introduce a social media depression index that may serve to characterize levels of depression in populations. Geographical, demographic and seasonal patterns of depression given by the measure confirm psychiatric findings and correlate highly with depression statistics reported by the Centers for Disease Control and Prevention (CDC)."