Semi-automatic Approach Research Articles

Automating DUID methods using robotics for rapid high throughput sample preparation – Section 4 and Section 5A UK Road Traffic Act Compounds in Whole Blood

To fully automate a 96-well plate sample preparation technique using liquid handling robotics for the purpose of significantly increasing sample throughput for whole blood samples taken under the UK Road Traffic Act (RTA). Introduction: demand for analysis of whole blood samples taken under the Road Traffic Act 1988 has increased in recent years due to UK Policing and Government policy on tackling driving under the influence of drugs (DUID). Previous extraction techniques utilised by our laboratory include manual or semi-automated approaches that are lengthy and labour intensive. Both approaches require time consuming human input, to precipitate blood and prepare calibrators and quality controls. Recent developments have sped up chromatographic methods through use of techniques such as ultra-high performance liquid chromatography. However, there has been little progress with speeding up sample preparation and extraction processes, particularly for whole blood to compliment increased LC-MS/MS capacity. Use of 96-well plate formats for protein precipitation and extraction provide a platform that can be readily coupled to automated liquid handling (ALH) instruments. This provides a solution to the increase in demand by allowing for extraction of more samples, with minimal human input, in a much shorter amount of time. Here we present development, validation and implementation of an automated robotic sample preparation method for whole blood for analysis of drugs in RTA cases. Aliquots (200 μL) of blank blood and casework samples were dispensed into a 96-well plate using a robotic pipetting system before being loaded onto a Hamilton ALH. Casework samples and blank blood were spiked with internal standard. Additional blank blood samples were further spiked to produce calibrants and quality controls. The plate was mixed with the addition of a cell lysis solution and the aliquots transferred to a protein/lipid depletion (PPT) plate. A positive pressure manifold was used to draw the solution through the PPT plate into a collection plate where the precipitate was dried. The precipitate was reconstituted and loaded by the Hamilton onto a microelution SPE plate. Following extraction, the samples were reconstituted and the collection plate placed in the LC-MS/MS autosampler for analysis. The LC-MS/MS method consists of a 2.1 mm × 30 mm, 1.7 μm, C18 column running a 4 minute gradient of water and methanol with 0.1% formic acid. Quantitation of 34 compounds (including common drugs of abuse and their metabolites) was successfully validated with CVs ranging from 3.0%–9.0% and accuracies of 85.8%–111.7%. Within batch precision had CVs of < 10.0%. The robotic platform was able to undertake sample pre-treatment and extraction of 40 case samples in 3.5 hours. The method was implemented into casework following UKAS accreditation and in 2021, 12,400 samples were analysed using the method. Introduction of this method to our laboratory has resulted in a significant increase in speed for a sample to be processed and results obtained. Each ALH is capable of extracting two batches per day; equating to 160 case sample versus 28 cases on semi-automated methods. This, along with a reduced sample volume requirement and reduced solvent consumption has had a very beneficial impact in terms of cost, turnaround times and ability to use low sample volume cases. Full automation of sample preparation of whole blood samples coupled with high speed chromatographic techniques can significantly increase throughput, decrease turnaround times and reduce solvent consumption.

A new use for old drugs: identifying compounds with an anti-obesity effect using a high through-put semi-automated Caenorhabditis elegans screening platform

Obesity is one of the most common global health problems for all age groups with obese people at risk of a variety of associated health complications. Consequently, there is a need to develop new therapies that lower body fat without the side effects. However, obesity is a complex and systemic disease, so that in vitro results are not easily translatable to clinical situations. A promising way to circumnavigate these issues is to reposition already approved drugs for new treatments, enabling a more streamlined drug discovery process due to the availability of pre-existing pharmacological and toxicological datasets. Chemical libraries, such as the Prestwick Chemical Library of 1200 FDA approved drugs, are available for this purpose. We have developed a simple semi-automated whole-organism approach to screening the Prestwick Chemical Library for those compounds which reduce fat content using the model organism Caenorhabditis elegans.Our whole-organism approach to high-throughput screening identified 9 “lead” compounds that reduced fat within 2 weeks in the model. Further screening and analysis provided 4 “hit” compounds (Midodrine, Vinpocetine, Fenoprofen and Lamivudine) that showed significant promise as drugs to reduce fat levels. The effects of these candidates were found to further reduce fat content in nematodes where an nhr-49/PPAR mutation resulted in “overweight” worms. Upon unblinding the “hit” compounds, they were found to have recently been shown to have anti-obesity effects in mammalian models too. In developing a whole-animal chemical screen to identify pharmacological agents as potential anti-obesity compounds, we demonstrate how chemical libraries can be rapidly and relatively cheaply profiled for active hits. Using the nematode Caenorhabditis elegans thus enables drugs to be assessed for applicability in humans and provides a new incentive to explore drug repurposing as a feasible and efficient way to identify new anti-obesity compounds.

Fundamental Research on Detecting Contradictions in Requirements: Taxonomy and Semi-Automated Approach

Requirements documents can contain several thousand individual requirements. They must be error-free to avoid unnecessary complications and costs in the later product development stages. An important part of this is to identify contradictions between two requirements. The first step is therefore to define what contradictions are and in what form they can occur in requirement documents. In this paper the scientific theories regarding contradictions are discussed, concerning to their usefulness for the topic. In doing so, the Aristotelian Logic proved to provide the best basis for an application in the Requirements Engineering context. Based on this theory, we have created specific subtypes of contradictions to match them to the requirements engineering field. The identification of these subtypes is done by a formalization of the requirement sentences and a subsequent analysis by means of simple questions. To validate the method, industrial requirement documents were searched for contradictions. For each detected type of contradiction, we present an example of the detection process. Thereby, we show that the method is easy to apply and may also be used by non-specialists. Thus, our method provides a taxonomy as a basis for further research on automated contradiction detection as well as on automated quality analysis of requirements documents.

Detection of spicules termed rapid blueshifted excursions as seen in the chromosphere via H α and the transition region via Si iv 1394 Å line emission

ABSTRACT We show signatures of spicules termed rapid blueshifted excursions (RBEs) in the Si iv 1394 Å emission line using a semi-automated detection approach. We use the H α filtergrams obtained by the CRISP imaging spectropolarimeter on the Swedish 1-m Solar Telescope and co-aligned Interface Region Imaging Spectrograph data using the SJI 1400 Å channel to study the spatiotemporal signature of the RBEs in the transition region. The detection of RBEs is carried out using an oriented coronal loop tracing algorithm on H α Dopplergrams at ±35 km s−1. We find that the number of detected features is significantly impacted by the time-varying contrast values of the detection images, which are caused by the changes in the atmospheric seeing conditions. We detect 407 events with lifetime greater than 32 s. This number is further reduced to 168 RBEs based on the H α profile and the proximity of RBEs to the large-scale flow. Of these 168 RBEs, 89 of them display a clear spatiotemporal signature in the SJI 1400 Å channel, indicating that a total of $\sim 53{{\ \rm per\ cent}}$ are observed to have co-spatial signatures between the chromosphere and the transition region.

Automated Web application testing driven by pre-recorded test cases

There are fully automated approaches proposed for Web application testing. These approaches mainly rely on tools that explore an application by crawling it. The crawling process results in a state transition model, which is used for generating test cases. Although these approaches are fully automated, they consume too much time and they usually require manual configuration. This is due to the lack of insight and domain knowledge of crawling tools regarding the application under test. We propose a semi-automated approach instead. We introduce a tool that takes a set of recorded event sequences as input. These sequences can be captured during exploratory tests. They are replayed as pre-recorded test cases. They are also exploited for steering the crawling and test case generation process. We performed a case study with 5 Web applications. These applications were randomly tested with state-of-the-art tools. Our approach can reduce the crawling time by hours, while compromising the coverage achieved by 0.2% to 7.43%. In addition, our tool does not require manual configuration before crawling. The input for the tool was created within 15 min of exploratory testing.

SDCF: semi-automatically structured dataset of citation functions

There is increasing research interest in the automatic detection of citation functions, which is why authors of academic papers cite previous works. A machine learning approach for such a task requires a large dataset consisting of varied labels of citation functions. However, existing datasets contain a few instances and a limited number of labels. Furthermore, most labels have been built using narrow research fields. Addressing these issues, this paper proposes a semiautomatic approach to develop a large dataset of citation functions based on two types of datasets. The first type contains 5668 manually labeled instances to develop a new labeling scheme of citation functions, and the second type is the final dataset that is built automatically. Our labeling scheme covers papers from various areas of computer science, resulting in five coarse labels and 21 fine-grained labels. To validate the scheme, two annotators were employed for annotation experiments on 421 instances that produced Cohen’s Kappa values of 0.85 for coarse labels and 0.71 for fine-grained labels. Following this, we performed two classification stages, i.e., filtering, and fine-grained to build models using the first dataset. The classification followed several scenarios, including active learning (AL) in a low-resource setting. Our experiments show that Bidirectional Encoder Representations from Transformers (BERT)-based AL achieved 90.29% accuracy, which outperformed other methods in the filtering stage. In the fine-grained stage, the SciBERT-based AL strategy achieved a competitive 81.15% accuracy, which was slightly lower than the non-AL strategy. These results show that the AL is promising since it requires less than half of the dataset. Considering the number of labels, this paper released the largest dataset consisting of 1,840,815 instances.

A disector-based framework for the automatic optical fractionator

Stereology-based methods provide the current state-of-the-art approaches for accurate quantification of numbers and other morphometric parameters of biological objects in stained tissue sections. The advent of artificial intelligence (AI)-based deep learning (DL) offers the possibility of improving throughput by automating the collection of stereology data. We have recently shown that DL can effectively achieve comparable accuracy to manual stereology but with higher repeatability, improved throughput, and less variation due to human factors by quantifying the total number of immunostained cells at their maximal profile of focus in extended depth of field (EDF) images. In the first of two novel contributions in this work, we propose a semi-automatic approach using a handcrafted Adaptive Segmentation Algorithm (ASA) to automatically generate ground truth on EDF images for training our deep learning (DL) models to automatically count cells using unbiased stereology methods. This update increases the amount of training data, thereby improving the accuracy and efficiency of automatic cell counting methods, without a requirement for extra expert time. The second contribution of this work is a Multi-channel Input and Multi-channel Output (MIMO) method using a U-Net deep learning architecture for automatic cell counting in a stack of z-axis images (also known as disector stacks). This DL-based digital automation of the ordinary optical fractionator ensures accurate counts through spatial separation of stained cells in the z-plane, thereby avoiding false negatives from overlapping cells in EDF images without the shortcomings of 3D and recurrent DL models. The contribution overcomes the issue of under-counting errors with EDF images due to overlapping cells in the z-plane (masking). We demonstrate the practical applications of these advances with automatic disector-based estimates of the total number of NeuN-immunostained neurons in a mouse neocortex. In summary, this work provides the first demonstration of automatic estimation of a total cell number in tissue sections using a combination of deep learning and the disector-based optical fractionator method.

Incorporating InSAR kinematics into rock glacier inventories: insights from 11 regions worldwide

Abstract. Rock glaciers are landforms related to permafrost creep that are sensitive to climate variability and change. Their spatial distribution and kinematic behaviour can be critical for managing water resources and geohazards in periglacial areas. Rock glaciers have been inventoried for decades worldwide, often without assessment of their kinematics. The availability of remote sensing data however makes the inclusion of kinematic information potentially feasible, but requires a common methodology in order to create homogeneous inventories. In this context, the International Permafrost Association (IPA) Action Group on rock glacier inventories and kinematics (2018–2023), with the support of the European Space Agency (ESA) Permafrost Climate Change Initiative (CCI) project, is defining standard guidelines for the inclusion of kinematic information within inventories. Here, we demonstrate the feasibility of applying common rules proposed by the Action Group in 11 regions worldwide. Spaceborne interferometric synthetic aperture radar (InSAR) was used to characterise identifiable moving areas related to rock glaciers, applying a manual and a semi-automated approach. Subsequently, these areas were used to assign kinematic information to rock glaciers in existing or newly compiled inventories. More than 5000 moving areas and more than 3600 rock glaciers were classified according to their kinematics. The method and the preliminary results were analysed. We identified drawbacks related to the intrinsic limitations of InSAR and to various applied strategies regarding the integration of non-moving rock glaciers in some investigated regions. This is the first internationally coordinated work that incorporates kinematic attributes within rock glacier inventories at a global scale. The results show the value of designing standardised inventorying procedures for periglacial geomorphology.

Mapping Arable Land and Permanent Agriculture Extent and Change in Southern Greece Using the European Union LUCAS Survey and a 35-Year Landsat Time Series Analysis

Agricultural land extent and change information is needed to assess food security, the effectiveness of land use policy, and both environmental and societal impacts. This information is especially valuable in biodiversity hotspots such as the Mediterranean region, where agricultural land expansion can result in detrimental effects such as soil erosion and the loss of native species. There has also been a growing concern that changing agricultural extent in fire-prone regions of the Mediterranean may increase fire risk due to accumulation of fuel in abandoned areas. In this study, we assessed the extent and change of agricultural land in Southern Greece from 1986 to 2020 using a combined European Land Use/Cover Area frame Survey (LUCAS) and Landsat time series approach. The LUCAS data and Landsat spectral-temporal metrics were used to train a random forest classifier, which was used to classify arable land and permanent agriculture (e.g., olive orchards, vineyards) at annual time steps. A post-processing step was taken to reduce spurious landcover class transitions using transition likelihoods and annual class membership likelihoods. A validation dataset consisting of 2666 samples, identified via a stratified random sampling approach and high-resolution imagery and time series analysis, were used to evaluate stable and change strata accuracies. Overall accuracies were greater than 70% and strata-specific accuracies were highly variable between stable and change strata. The results show that southern Greece has experienced a recent gain in arable land (~12,000 ha from ~2009–2020) and a much larger gain in permanent agriculture (&gt;115,000 ha from ~1993–2020). Arable land loss mainly occurred from 1987 to ~2002 when extent decreased by 15,000 ha, of which 66% was abandoned. The semi-automated approach described in this paper provides a promising approach for monitoring agricultural land change and enabling assessments of agriculture policy effectiveness and environmental impacts.

Aggregate Channel Features for newborn face detection in Neonatal Intensive Care Units.

An efficient face detector could be very helpful to point out possible neurological dysfunctions such as seizure events in Neonatal Intensive Care Units. However, its development is still challenging because large public datasets of newborns' faces are missing. Over the years several studies introduced semi-automatic approaches. This study proposes a fully automated face detector for newborns in Neonatal Intensive Care Units, based on the Aggregate Channel Feature algorithm. The developed method is tested on a dataset of video recordings from 42 full-term newborns collected at the Neuro-physiopathology and Neonatology Clinical Units, AOU Careggi, Firenze, Italy. The proposed system showed promising results, giving (mean ± standard error): log-Average Miss Rate = 0.47 ± 0.05 and Average Precision Recall = 0.61 ± 0.05. Moreover, achieved results highlighted interesting differences between newborns without seizures, newborns with electro-clinical seizures, and newborns with electrographic-only seizures. For both metrics statistically significant differences were found between patients with electro-clinical seizures and the other two groups. Clinical Relevance- The proposed method, based on quantitative physio-pathological features of facial movements, is of clinical relevance as it could speed up pain or seizure assessment of newborns in Neonatal Intensive Care Units.

Remote sensing based mapping of Tillandsia fields - A semi-automatic detection approach in the hyperarid coastal Atacama Desert, northern Chile

Unique fog ecosystems that occur inland along the Chilean coastal desert are dominated by Tillandsia landbeckii. The average annual precipitation in this hyperarid area lies below 1 mm per year. Tillandsia are specialized in the foliar uptake of fog as a main source of water. The detailed mapping of the distribution of Tillandsia is lacking, making it difficult to understand their geo-ecological niche and to determine the impacts that climate change may have on this species. The objective of this study is to create a detailed spatial distribution of Tillandsia in the Atacama Desert in northern Chile based on remote sensing semi-automatic detection process. For this purpose, high-resolution WorldView-3 optical satellite data has been acquired. The extraction of Tillandsia was done with ENVI Deep Learning tools. As a result, a map of Tillandsia has been created. Several fields were found between Cerro Huantajaya in the north and Cerro Soronal in the south in the study area between 800 and 1300 m a.s.l. For validation purposes ground truth data has been used. The overall accuracy of this classification is 92.02%. The results can be used as a basis for geo-ecological niche modeling, further monitoring and for the development of conservation strategies.

A semi-automated hybrid approach to identify radicalization on social digital platform

The &lt;span&gt;digital social platform is an important medium for sharing or communicating a message from one person to another or one to many. The growth of internet users and social media use has also led to many adverse consequences. Such a platform is also used for radical activity by spreading the radical message in public. The detection of such a message is impossible by human monitoring. Many researchers are continually working on automatic detection of such activity to find a way to stop it. Automatic identification is also not possible due to the massive amount of data present and ambiguity in messages. The proposed work presents a framework for detecting the radical message and taking action by automatically blocking it. A dataset of 33k tweets has been fetched from twitter based on radical words. Two machine learning models, first countervectorizer and Logistic regression-based and second convolutional neural networks (CNN) have been applied yielding 96.97% accuracy. The provision of human intervention is also given in doubt cases which helps further to improve the accuracy of overall model. The framework gives very good results in a simulated environment&lt;/span&gt;.

From GWT to Angular: An Experiment Report on Migrating a Legacy Web Application

Because Google Web Toolkit (GWT) is no longer actively maintained, Berger-Levrault decided to migrate its applications to Angular. We designed a semiautomated migration approach that helps developers migrate applications’ front ends from GWT to Angular and a tool that performs the migration.

Parenting online: analyzing information provided by parenting-focused Twitter accounts

ABSTRACT This study investigated the content of parenting information shared on social media by identifying the range and frequency of topics shared by parenting-focused accounts on Twitter. Using the Twitter API, a universe of 675,069 tweets were gathered from 74 of the most-followed parenting-focused accounts, or “hubs,” from January 2016 to June 2018. Using a custom, semi-automated topic modeling approach, we identified the topics – and subtopics within topics – parenting hubs shared with their followers and investigated whether any meaningful differences in topical focus existed between accounts targeting mothers versus fathers. Results indicate that over one third of tweets were about Parenting Behavior and nearly one quarter about Health, with Entertainment, School and Motherhood and Fatherhood generally as less tweeted topics. Mother-focused accounts tweeted more about Health than father-focused accounts, which tweeted more than others about Entertainment. Implications for future parenting and social media research are discussed.

Semi-automatic service value network modeling approach based on external public data

Semi-automatic service value network modeling approach based on external public data

Leveraging COBIT 2019 to Implement IT Governance in SME Context: A Case Study of Higher Education in Campus A

Achieving business and Information Technology (IT) alignment has become the aspiration of most organizations nowadays. Small and Medium Enterprises (SMEs) are not exempt as they also thrive to survive in a competitive market using IT. However, implementing all IT control and management components will be excessive, with a lack of justifiable cost-benefit for SMEs. A tailored governance system based on the specificities of SMEs is necessitated to help the organization to focus on its main objectives and strategies. By leveraging COBIT 2019 design toolkit, the researchers support Campus A in establishing healthy governance and IT management. Both qualitative and quantitative approaches are applied to select relevant governance/ management objectives. The toolkit has been designed with a semi-automated quantitative approach in which users will get scoring for each objective based on the associated value inputted for each design factor. Through a series of discussions with the management team, it concludes the governance design and recommends several improvements to increase its capability level, from the current level of 1.05 (initial stage) to the desired level of 2.33 (repeatable stage). Then, since the toolkit is practical to use, it is also rigid by design with its predefined and protected formula. To some extent, the resulting score or importance level of certain governance/management objectives is questionable and lacks justification. Flags or indicators to ‘should-have’ governance/management objectives, regardless of the organization’s size and type, will be useful to prevent the omission of essential objectives.

Harmonization of Measurement Codes for Concept-Oriented Lab Data Retrieval.

Measurement concepts are essential to observational healthcare research; however, a lack of concept harmonization limits the quality of research that can be done on multisite research networks. We developed five methods that used a combination of automated, semi-automated and manual approaches for generating measurement concept sets. We validated our concept sets by calculating their frequencies in cohorts from the Columbia University Irving Medical Center (CUIMC) database. For heart transplant patients, the preoperative frequencies of basic metabolic panel concept sets, which we generated by a semi-automated approach, were greater than 99%. We also made concept sets for lumbar puncture and coagulation panels, by automated and manual methods respectively.

Automated Multi-Scale and Multivariate Geological Logging from Drill-Core Hyperspectral Data

Hyperspectral drill-core scanning adds value to exploration campaigns by providing continuous, high-resolution mineralogical data over the length of entire boreholes. However, multivariate mineralogical data must be transformed into lithological domains such that it is compatible with interpolation techniques and be usable for geomodeling. Manual interpretation of multivariate drill-core data is a challenging, time-consuming and subjective task, and automated or semi-automated approaches are needed. However, naive machine-learning techniques that ignore the distinct spatial structure and multi-scale nature of geological systems tend to produce geologically unreasonable results. Automated geological logging and multi-scale hierarchical domaining of drill-cores has been previously addressed in several studies by means of scalograms from a wavelet transform and tessellation, albeit exploiting only univariate information. The methodology involves the extraction of the local first principal component at a neighborhood of each observation, and the segmentation of the resulting series of scores with a continuous wavelet transform for boundary detection. In this way, the correlation pattern between the variables is incorporated into the segmentation. The scalogram accurately locates the geological boundaries at depth and yields hierarchical geological domains with mineralogical composition characteristics. The performance of this approach is demonstrated on a synthetic as well as a real multivariate dataset. The real dataset consists of mineral abundances derived from drill-core hyperspectral imaging data acquired in Elvira, a shale-hosted volcanogenic massive sulfide deposit located in the Iberian Pyrite Belt, where 7000 m of drill-core were acquired along 80 boreholes. The extracted domains are sensible from a geological point of view and spatially coherent across the boreholes in cross-sections. The results at relevant scales were qualitatively validated by comparing against the lithological log. This method is fast, is appropriate for multivariate geological data along boreholes, and provides a choice of scales for hierarchical geological domains along boreholes with mineralogical composition characteristics that can be modeled in 3D. Our approach provides an automatic way to transform hyperspectral image-derived mineral maps into vertically coherent geological units that are appropriate inputs for 3D geological modeling workflows. Moreover, the method improves the boundary detection and geological domaining by making use of multivariate information.

Construction and Evaluation of a High-Quality Corpus for Legal Intelligence Using Semiautomated Approaches

A high-quality corpus is essential for building an effective legal intelligence system. The quality of a corpus includes both the quality of original data and the quality of its corresponding labeling. The major quality dimensions of a legal corpus include comprehensiveness, freshness, and correctness. However, building a comprehensive, correct, and fresh legal corpus is a grand challenge. In this article, we propose a semiautomated machine learning framework to address the challenge. We first created an initial corpus with 4937 instances that were manually labeled. Several strategies were implemented to assure its quality. The initial results showed that class imbalance and insufficiency of training data are the two major quality issues that negatively impacted the quality of the system that was built on the data. We experimented and compared three class-imbalance-handling techniques and found that the mixed-sampling method, which combines upsampling and downsampling, was the most effective way to address the issue. In order to address the insufficiency of training data, we experimented several machine learning methods for automated data augmentation including pseudolabeling, co-training, expectation-maximization, and generative adversarial network (GAN). The results showed that GAN with deep learning models achieved the best performance. Finally, ensemble learning of different classifiers was proposed and experimented with for the construction of a legal corpus, which achieves higher quality in comprehensiveness, freshness, and correctness compared to existing work. The semiautomated machine learning framework and the data quality evaluation method developed in this research can be used for data augmentation and quality evaluation of a large dataset as well as a reference for the selection of machine learning methods for data augmentation and generation. The machine learning models, the training data, and the legal corpus are published and publicly accessible at [Online]. Available: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/haihua0913/legalArgumentmining</uri> .

Levering internet-based discussion data from gynecological cancer survivors to inform survivorship care: A mixed methods thematic analysis approach.

e24143 Background: Internet and social media platforms offer insight into the experience of survivorship, but the volume of narrative data is often cumbersome for thorough thematic analysis. We present a semi-automated mixed methods approach to analyze web-based discussions and demonstrate its utility on American Cancer Society (ACS) Discussion Board posts from gynecologic cancer survivors. Methods: Posts from the ACS Ovarian Cancer, Uterine Cancer, and Other Gynecological Cancer Discussion Boards were analyzed for psychosocial themes described in the Cancer Survivorship Care Framework. Quantitative analysis was facilitated by verified keywords created for each theme of interest and was completed via custom Python scripts and R packages. Qualitative analysis was expedited by theme keywords and completed on a subset of posts. Results: A total of 125,498 posts made by 6,436 gynecological cancer survivors and caregivers between July 2000 and February 2020 were evaluated. Of all posts, 23,458 were related to psychosocial aspects of survivorship and were analyzed. Quantitative analysis revealed that survivors frequently discussed the role of friends and family in care, fatigue, health insurance issues, and the effect of cancer on loved ones. The most frequently used psychosocial-related words were “family,” “hope,” and “help.” Qualitative analysis demonstrated that survivors frequently discussed coping and caregiver relationships, where survivors sought advice on topics including spousal emotional adjustment, financial toxicity, and confronting mortality. Conclusions: Online platforms offer great opportunity to learn about patient experiences of survivorship care. Candid conversations between survivors may be leveraged to inform survivorship practices and improve future survivorship initiatives. Our novel methodology expedites thematic analysis of such robust narrative data and its translation into survivorship settings.